Initial pass to add capability declarations to stdlib intrinsics. (#3912)

1 files changed, 1040 insertions, 635 deletions

diff --git a/source/slang/glsl.meta.slang b/source/slang/glsl.meta.slang
index e2c1d25bd..d04dfe8b9 100644
--- a/source/slang/glsl.meta.slang
+++ b/source/slang/glsl.meta.slang
@@ -9,8 +9,6 @@
 #define VECTOR_MAP_TRINARY(TYPE, COUNT, FUNC, A, B, C) \
     vector<TYPE,COUNT> result; for(int i = 0; i < COUNT; ++i) { result[i] = FUNC(A[i], B[i], C[i]); } return result
 
-#define REQUIRE_KHRONOS [require(glsl)] [require(spirv)]
-
 //
 // OpenGL 4.60 spec
 //
@@ -107,11 +105,11 @@ public in uvec3 gl_WorkGroupID : SV_GroupID;
 public in uvec3 gl_LocalInvocationIndex : SV_GroupIndex;
 public in uvec3 gl_LocalInvocationID : SV_GroupThreadID;
 
-[require(glsl)]
-[require(spirv)]
 public property uint3 gl_NumWorkGroups {
 
-    get {
+    [require(glsl_spirv, GLSL_430_SPIRV_1_0_compute)]
+    get 
+    {
         __target_switch
         {
         case glsl:
@@ -128,6 +126,7 @@ public property uint3 gl_NumWorkGroups {
 public property uint3 gl_WorkGroupSize
 {
     [__unsafeForceInlineEarly]
+    [require(glsl_spirv, GLSL_430_SPIRV_1_0_compute)]
     get
     {
         return WorkgroupSize();
@@ -153,6 +152,7 @@ public in int gl_ViewportIndex : SV_ViewportArrayIndex;
 
 [OverloadRank(15)]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public matrix<float, N, N> operator*<let N:int>(matrix<float, N, N> m1, matrix<float, N, N> m2)
 {
     return mul(m2, m1);
@@ -160,6 +160,7 @@ public matrix<float, N, N> operator*<let N:int>(matrix<float, N, N> m1, matrix<f
 
 [OverloadRank(15)]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public matrix<half, N, N> operator*<let N:int>(matrix<half, N, N> m1, matrix<half, N, N> m2)
 {
     return mul(m2, m1);
@@ -167,6 +168,7 @@ public matrix<half, N, N> operator*<let N:int>(matrix<half, N, N> m1, matrix<hal
 
 [OverloadRank(15)]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public matrix<double, N, N> operator*<let N:int>(matrix<double, N, N> m1, matrix<double, N, N> m2)
 {
     return mul(m2, m1);
@@ -174,6 +176,7 @@ public matrix<double, N, N> operator*<let N:int>(matrix<double, N, N> m1, matrix
 
 [ForceInline]
 [OverloadRank(15)]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public matrix<T, R, L> operator*<T:__BuiltinFloatingPointType, let L : int, let C : int, let R : int>(matrix<T, C, L> m1, matrix<T, R, C> m2)
 {
     return mul(m2, m1);
@@ -181,6 +184,7 @@ public matrix<T, R, L> operator*<T:__BuiltinFloatingPointType, let L : int, let
 
 [ForceInline]
 [OverloadRank(15)]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, R> operator*<T:__BuiltinFloatingPointType, let C : int, let R : int>(vector<T, C> v, matrix<T, R, C> m)
 {
     return mul(m, v);
@@ -188,6 +192,7 @@ public vector<T, R> operator*<T:__BuiltinFloatingPointType, let C : int, let R :
 
 [ForceInline]
 [OverloadRank(15)]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, C> operator*<T:__BuiltinFloatingPointType, let C : int, let R : int>(matrix<T, R, C> m, vector<T, R> v)
 {
     return mul(v, m);
@@ -224,6 +229,7 @@ public extension vector<T, 3>
 
 [ForceInline]
 [OverloadRank(15)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator==<T:__BuiltinArithmeticType, let N:int>(vector<T, N> left, vector<T, N> right)
 {
     return all(equal(left, right));
@@ -231,6 +237,7 @@ public bool operator==<T:__BuiltinArithmeticType, let N:int>(vector<T, N> left,
 
 [ForceInline]
 [OverloadRank(15)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator!=<T:__BuiltinArithmeticType, let N:int>(vector<T, N> left, vector<T, N> right)
 {
     return any(notEqual(left, right));
@@ -238,6 +245,7 @@ public bool operator!=<T:__BuiltinArithmeticType, let N:int>(vector<T, N> left,
 
 [ForceInline]
 [OverloadRank(14)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator==<T:__BuiltinFloatingPointType, let N:int>(vector<T, N> left, vector<T, N> right)
 {
     return all(equal(left, right));
@@ -245,6 +253,7 @@ public bool operator==<T:__BuiltinFloatingPointType, let N:int>(vector<T, N> lef
 
 [ForceInline]
 [OverloadRank(14)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator!=<T:__BuiltinFloatingPointType, let N:int>(vector<T, N> left, vector<T, N> right)
 {
     return any(notEqual(left, right));
@@ -252,6 +261,7 @@ public bool operator!=<T:__BuiltinFloatingPointType, let N:int>(vector<T, N> lef
 
 [ForceInline]
 [OverloadRank(14)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator==<T:__BuiltinLogicalType, let N:int>(vector<T, N> left, vector<T, N> right)
 {
     return all(equal(left, right));
@@ -259,6 +269,7 @@ public bool operator==<T:__BuiltinLogicalType, let N:int>(vector<T, N> left, vec
 
 [ForceInline]
 [OverloadRank(14)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator!=<T:__BuiltinLogicalType, let N:int>(vector<T, N> left, vector<T, N> right)
 {
     return any(notEqual(left, right));
@@ -271,6 +282,7 @@ for (auto type : kBaseTypes) {
 }}}}
 [ForceInline]
 [OverloadRank(15)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator==<let N:int>(vector<$(typeName), N> left, vector<$(typeName), N> right)
 {
     return all(equal(left, right));
@@ -278,6 +290,7 @@ public bool operator==<let N:int>(vector<$(typeName), N> left, vector<$(typeName
 
 [ForceInline]
 [OverloadRank(15)]
+[require(cpp_cuda_glsl_hlsl_spirv)]
 public bool operator!=<let N:int>(vector<$(typeName), N> left, vector<$(typeName), N> right)
 {
     return any(notEqual(left, right));
@@ -293,6 +306,7 @@ ${{{{
 __generic<T : __BuiltinFloatingPointType>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public T atan(T y, T x)
 {
     return atan2(y, x);
@@ -301,6 +315,7 @@ public T atan(T y, T x)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T,N> atan(vector<T,N> y, vector<T,N> x)
 {
     return atan2(y, x);
@@ -311,6 +326,7 @@ __target_intrinsic(cuda, "$P_asinh($0)")
 __target_intrinsic(cpp, "$P_asinh($0)")
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public T asinh(T x)
 {
     return log(x + sqrt(x * x + T(1)));
@@ -319,6 +335,7 @@ public T asinh(T x)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public vector<T,N> asinh(vector<T,N> x)
 {
     VECTOR_MAP_UNARY(T, N, asinh, x);
@@ -329,6 +346,7 @@ __target_intrinsic(cuda, "$P_acosh($0)")
 __target_intrinsic(cpp, "$P_acosh($0)")
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public T acosh(T x)
 {
     return log(x + sqrt( x * x - T(1)));
@@ -337,6 +355,7 @@ public T acosh(T x)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public vector<T,N> acosh(vector<T,N> x)
 {
     VECTOR_MAP_UNARY(T, N, acosh, x);
@@ -347,6 +366,7 @@ __target_intrinsic(cuda, "$P_atanh($0)")
 __target_intrinsic(cpp, "$P_atanh($0)")
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public T atanh(T x)
 {
     return T(0.5) * log((T(1) + x) / (T(1) - x));
@@ -355,6 +375,7 @@ public T atanh(T x)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T,N> atanh(vector<T,N> x)
 {
     VECTOR_MAP_UNARY(T, N, atanh, x);
@@ -367,6 +388,7 @@ public vector<T,N> atanh(vector<T,N> x)
 __generic<T : __BuiltinFloatingPointType>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public T inversesqrt(T x)
 {
     return rsqrt(x);
@@ -375,6 +397,7 @@ public T inversesqrt(T x)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public vector<T, N> inversesqrt(vector<T, N> x)
 {
     return rsqrt(x);
@@ -387,6 +410,7 @@ public vector<T, N> inversesqrt(vector<T, N> x)
 __generic<T : __BuiltinFloatingPointType>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public T roundEven(T x)
 {
     T i;
@@ -404,6 +428,7 @@ public T roundEven(T x)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_130)]
 public vector<T,N> roundEven(vector<T,N> x)
 {
     VECTOR_MAP_UNARY(T, N, roundEven, x);
@@ -412,6 +437,7 @@ public vector<T,N> roundEven(vector<T,N> x)
 __generic<T : __BuiltinFloatingPointType>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public T fract(T x)
 {
     return frac(x);
@@ -420,6 +446,7 @@ public T fract(T x)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, N> fract(vector<T, N> x)
 {
     return frac(x);
@@ -428,6 +455,7 @@ public vector<T, N> fract(vector<T, N> x)
 __generic<T : __BuiltinFloatingPointType>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public T mod(T x, T y)
 {
     return fmod(x, y);
@@ -436,6 +464,7 @@ public T mod(T x, T y)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, N> mod(vector<T, N> x, T y)
 {
     return fmod(x, vector<T, N>(y));
@@ -444,6 +473,7 @@ public vector<T, N> mod(vector<T, N> x, T y)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, N> mod(vector<T, N> x, vector<T, N> y)
 {
     return fmod(x, y);
@@ -452,6 +482,7 @@ public vector<T, N> mod(vector<T, N> x, vector<T, N> y)
 __generic<T : __BuiltinFloatingPointType>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public T mix(T x, T y, T a)
 {
     return lerp(x, y, a);
@@ -460,6 +491,7 @@ public T mix(T x, T y, T a)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, N> mix(vector<T, N> x, vector<T, N> y, T a)
 {
     return lerp(x, y, vector<T, N>(a));
@@ -468,6 +500,7 @@ public vector<T, N> mix(vector<T, N> x, vector<T, N> y, T a)
 __generic<T : __BuiltinFloatingPointType, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, N> mix(vector<T, N> x, vector<T, N> y, vector<T, N> a)
 {
     return lerp(x, y, a);
@@ -476,6 +509,7 @@ public vector<T, N> mix(vector<T, N> x, vector<T, N> y, vector<T, N> a)
 __generic<T>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public T mix(T x, T y, bool a)
 {
     return (a ? y : x);
@@ -484,6 +518,7 @@ public T mix(T x, T y, bool a)
 __generic<T, let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, sm_2_0_GLSL_140)]
 public vector<T, N> mix(vector<T, N> x, vector<T, N> y, vector<bool, N> a)
 {
     vector<T, N> result;
@@ -496,6 +531,7 @@ public vector<T, N> mix(vector<T, N> x, vector<T, N> y, vector<bool, N> a)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public int floatBitsToInt(highp float x)
 {
     return asint(x);
@@ -504,6 +540,7 @@ public int floatBitsToInt(highp float x)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vector<int, N> floatBitsToInt(highp vector<float, N> x)
 {
     return asint(x);
@@ -511,6 +548,7 @@ public vector<int, N> floatBitsToInt(highp vector<float, N> x)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public uint floatBitsToUint(highp float x)
 {
     return asuint(x);
@@ -519,6 +557,7 @@ public uint floatBitsToUint(highp float x)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vector<uint, N> floatBitsToUint(highp vector<float, N> x)
 {
     return asuint(x);
@@ -526,6 +565,7 @@ public vector<uint, N> floatBitsToUint(highp vector<float, N> x)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public float intBitsToFloat(highp int x)
 {
     return asfloat(x);
@@ -534,6 +574,7 @@ public float intBitsToFloat(highp int x)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vector<float, N> intBitsToFloat(highp vector<int, N> x)
 {
     return asfloat(x);
@@ -541,6 +582,7 @@ public vector<float, N> intBitsToFloat(highp vector<int, N> x)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public float uintBitsToFloat(highp uint x)
 {
     return asfloat(x);
@@ -549,6 +591,7 @@ public float uintBitsToFloat(highp uint x)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vector<float, N> uintBitsToFloat(highp vector<uint, N> x)
 {
     return asfloat(x);
@@ -616,6 +659,7 @@ float unpackSnorm1x8(uint p)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 uint float2half(float f)
 {
     uint u = floatBitsToUint(f);
@@ -632,6 +676,7 @@ uint float2half(float f)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public uint packUnorm2x16(vec2 v)
 {
     return packUnorm1x16(v.x) | (packUnorm1x16(v.y) << uint(16));
@@ -640,6 +685,7 @@ public uint packUnorm2x16(vec2 v)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public uint packSnorm2x16(vec2 v)
 {
     return packSnorm1x16(v.x) | (packSnorm1x16(v.y) << uint(16));
@@ -648,6 +694,7 @@ public uint packSnorm2x16(vec2 v)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public uint packUnorm4x8(vec4 v)
 {
     return packUnorm1x8(v.x) | (packUnorm1x8(v.y) << uint(8)) | (packUnorm1x8(v.z) << uint(16)) | (packUnorm1x8(v.w) << uint(24));
@@ -656,6 +703,7 @@ public uint packUnorm4x8(vec4 v)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public uint packSnorm4x8(vec4 v)
 {
     return packSnorm1x8(v.x) | (packSnorm1x8(v.y) << uint(8)) | (packSnorm1x8(v.z) << uint(16)) | (packSnorm1x8(v.w) << uint(24));
@@ -664,6 +712,7 @@ public uint packSnorm4x8(vec4 v)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vec2 unpackUnorm2x16(uint p)
 {
     return vec2(unpackUnorm1x16(p & uint(0xffff)), unpackUnorm1x16(p >> uint(16)));
@@ -672,6 +721,7 @@ public vec2 unpackUnorm2x16(uint p)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vec2 unpackSnorm2x16(uint p)
 {
     return vec2(unpackSnorm1x16(p & uint(0xffff)), unpackSnorm1x16(p >> uint(16)));
@@ -680,6 +730,7 @@ public vec2 unpackSnorm2x16(uint p)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vec4 unpackUnorm4x8(highp uint p)
 {
     return vec4(unpackUnorm1x8(p & uint(0xffff)), unpackUnorm1x8(p >> uint(8)), unpackUnorm1x8(p >> uint(16)), unpackUnorm1x8(p >> uint(24)));
@@ -688,6 +739,7 @@ public vec4 unpackUnorm4x8(highp uint p)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vec4 unpackSnorm4x8(highp uint p)
 {
     return vec4(unpackSnorm1x8(p & uint(0xffff)), unpackSnorm1x8(p >> uint(8)), unpackSnorm1x8(p >> uint(16)), unpackSnorm1x8(p >> uint(24)));
@@ -696,6 +748,7 @@ public vec4 unpackSnorm4x8(highp uint p)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public uint packHalf2x16(vec2 v)
 {
     return float2half(v.x) | (float2half(v.y) << uint(16));
@@ -704,6 +757,7 @@ public uint packHalf2x16(vec2 v)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public float half2float(uint h)
 {
     uint s = ((h & uint(0x8000)) << uint(16));
@@ -719,6 +773,7 @@ public float half2float(uint h)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public vec2 unpackHalf2x16(uint p)
 {
     return vec2(half2float(p & uint(0xffff)), half2float(p >> uint(16)));
@@ -727,6 +782,7 @@ public vec2 unpackHalf2x16(uint p)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public double packDouble2x32(uvec2 v)
 {
     // TODO: there is no "asdouble()"
@@ -737,6 +793,7 @@ public double packDouble2x32(uvec2 v)
 __target_intrinsic(glsl)
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_4_0)]
 public uvec2 unpackDouble2x32(double v)
 {
     // TODO: there is no "asuint64()"
@@ -751,6 +808,7 @@ public uvec2 unpackDouble2x32(double v)
 __generic<T : __BuiltinFloatingPointType>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_400)]
 public T faceforward(T n, T i, T ng)
 {
     return dot(ng, i) < T(0.0f) ? n : -n;
@@ -782,6 +840,7 @@ public matrix<T, C, R> outerProduct(vector<T, C> c, vector<T, R> r)
 __generic<T : __BuiltinFloatingPointType, let N : int>
 __target_intrinsic(hlsl)
 __target_intrinsic(glsl)
+[require(cpp_cuda_glsl_hlsl_spirv, GLSL_400)]
 matrix<T,N,N> inverse(matrix<T,N,N> m);
 
 //
@@ -987,27 +1046,35 @@ public vector<uint,N> bitfieldReverse(highp vector<uint,N> value)
     VECTOR_MAP_UNARY(int, N, bitfieldReverse, value);
 }
 
-[__readNone] [ForceInline] REQUIRE_KHRONOS
+[__readNone] 
+[ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public uint bitCount(uint value)
 {
     return countbits(value);
 }
 
 __generic<let N:int>
-[__readNone] [ForceInline] REQUIRE_KHRONOS
+[__readNone] 
+[ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public vector<uint,N> bitCount(vector<uint,N> value)
 {
     VECTOR_MAP_UNARY(uint, N, countbits, value);
 }
 
-[__readNone] [ForceInline] REQUIRE_KHRONOS
+[__readNone] 
+[ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public int bitCount(int value)
 {
     return countbits(uint(value));
 }
     
 __generic<let N:int>
-[__readNone] [ForceInline] REQUIRE_KHRONOS
+[__readNone] 
+[ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public vector<int,N> bitCount(vector<int,N> value)
 {
     VECTOR_MAP_UNARY(int, N, countbits, value);
@@ -1015,6 +1082,7 @@ public vector<int,N> bitCount(vector<int,N> value)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public int findLSB(int v)
 {
     return firstbitlow(v);
@@ -1023,6 +1091,7 @@ public int findLSB(int v)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public vector<int,N> findLSB(vector<int,N> value)
 {
     return firstbitlow(value);
@@ -1030,6 +1099,7 @@ public vector<int,N> findLSB(vector<int,N> value)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public uint findLSB(uint v)
 {
     return firstbitlow(v);
@@ -1038,6 +1108,7 @@ public uint findLSB(uint v)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public vector<uint,N> findLSB(vector<uint,N> value)
 {
     return firstbitlow(value);
@@ -1045,6 +1116,7 @@ public vector<uint,N> findLSB(vector<uint,N> value)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public int findMSB(int value)
 {
     return firstbithigh(value);
@@ -1053,6 +1125,7 @@ public int findMSB(int value)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public vector<int,N> findMSB(vector<int,N> value)
 {
     return firstbithigh(value);
@@ -1060,6 +1133,7 @@ public vector<int,N> findMSB(vector<int,N> value)
 
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public uint findMSB(uint value)
 {
     return firstbithigh(value);
@@ -1068,6 +1142,7 @@ public uint findMSB(uint value)
 __generic<let N:int>
 [__readNone]
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, shader5_sm_5_0)]
 public vector<uint,N> findMSB(vector<uint,N> value)
 {
     return firstbithigh(value);
@@ -1243,6 +1318,7 @@ public typealias usamplerBuffer = SamplerBuffer<uint4>;
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public int textureSize(Sampler1D<vector<T,N>> sampler, int lod)
 {
     int result;
@@ -1253,6 +1329,7 @@ public int textureSize(Sampler1D<vector<T,N>> sampler, int lod)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec2 textureSize(Sampler2D<vector<T,N>> sampler, int lod)
 {
     vector<int,2> result;
@@ -1263,6 +1340,7 @@ public ivec2 textureSize(Sampler2D<vector<T,N>> sampler, int lod)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec3 textureSize(Sampler3D<vector<T,N>> sampler, int lod)
 {
     vector<int,3> result;
@@ -1273,6 +1351,7 @@ public ivec3 textureSize(Sampler3D<vector<T,N>> sampler, int lod)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec2 textureSize(SamplerCube<vector<T,N>> sampler, int lod)
 {
     vector<int,2> result;
@@ -1282,6 +1361,7 @@ public ivec2 textureSize(SamplerCube<vector<T,N>> sampler, int lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public int textureSize(sampler1DShadow sampler, int lod)
 {
     int result;
@@ -1291,6 +1371,7 @@ public int textureSize(sampler1DShadow sampler, int lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec2 textureSize(sampler2DShadow sampler, int lod)
 {
     vector<int,2> result;
@@ -1300,6 +1381,7 @@ public ivec2 textureSize(sampler2DShadow sampler, int lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec2 textureSize(samplerCubeShadow sampler, int lod)
 {
     vector<int,2> result;
@@ -1308,6 +1390,7 @@ public ivec2 textureSize(samplerCubeShadow sampler, int lod)
     return result;
 }
 
+[require(glsl_hlsl_spirv, texture_size)]
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
 public ivec3 textureSize(SamplerCubeArray<vector<T,N>> sampler, int lod)
@@ -1319,6 +1402,7 @@ public ivec3 textureSize(SamplerCubeArray<vector<T,N>> sampler, int lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec3 textureSize(samplerCubeArrayShadow sampler, int lod)
 {
     vector<int,3> result;
@@ -1327,6 +1411,7 @@ public ivec3 textureSize(samplerCubeArrayShadow sampler, int lod)
     return result;
 }
 
+[require(glsl_hlsl_spirv, texture_size)]
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
 public ivec2 textureSize(Sampler2DRect<vector<T,N>> sampler)
@@ -1338,6 +1423,7 @@ public ivec2 textureSize(Sampler2DRect<vector<T,N>> sampler)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec2 textureSize(sampler2DRectShadow sampler)
 {
     vector<int,2> result;
@@ -1346,6 +1432,7 @@ public ivec2 textureSize(sampler2DRectShadow sampler)
     return result;
 }
 
+[require(glsl_hlsl_spirv, texture_size)]
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
 public ivec2 textureSize(Sampler1DArray<vector<T,N>> sampler, int lod)
@@ -1357,6 +1444,7 @@ public ivec2 textureSize(Sampler1DArray<vector<T,N>> sampler, int lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec2 textureSize(sampler1DArrayShadow sampler, int lod)
 {
     vector<int,2> result;
@@ -1365,6 +1453,7 @@ public ivec2 textureSize(sampler1DArrayShadow sampler, int lod)
     return result;
 }
 
+[require(glsl_hlsl_spirv, texture_size)]
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
 public ivec3 textureSize(Sampler2DArray<vector<T,N>> sampler, int lod)
@@ -1376,6 +1465,7 @@ public ivec3 textureSize(Sampler2DArray<vector<T,N>> sampler, int lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_size)]
 public ivec3 textureSize(sampler2DArrayShadow sampler, int lod)
 {
     vector<int,3> result;
@@ -1384,6 +1474,7 @@ public ivec3 textureSize(sampler2DArrayShadow sampler, int lod)
     return result;
 }
 
+[require(glsl_hlsl_spirv, texture_size)]
 __generic<T:__BuiltinArithmeticType, let N:int, let format:int>
 [ForceInline]
 public int textureSize(SamplerBuffer<vector<T,N>,format> sampler)
@@ -1393,6 +1484,7 @@ public int textureSize(SamplerBuffer<vector<T,N>,format> sampler)
     return int(result);
 }
 
+[require(glsl_hlsl_spirv, texture_size)]
 __generic<T:__BuiltinArithmeticType, let N:int, let sampleCount:int>
 [ForceInline]
 public ivec2 textureSize(Sampler2DMS<vector<T,N>,sampleCount> sampler)
@@ -1404,6 +1496,7 @@ public ivec2 textureSize(Sampler2DMS<vector<T,N>,sampleCount> sampler)
     return result;
 }
 
+[require(glsl_hlsl_spirv, texture_size)]
 __generic<T:__BuiltinArithmeticType, let N:int, let sampleCount:int>
 [ForceInline]
 public ivec3 textureSize(Sampler2DMSArray<vector<T,N>,sampleCount> sampler)
@@ -1421,6 +1514,7 @@ public ivec3 textureSize(Sampler2DMSArray<vector<T,N>,sampleCount> sampler)
 
 __generic<T:IFloat, let isArray:int, let sampleCount:int, let isShadow:int, let format:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylod)]
 public vec2 textureQueryLod(__TextureImpl<
         T,
         __Shape1D,
@@ -1441,6 +1535,7 @@ public vec2 textureQueryLod(__TextureImpl<
 
 __generic<T:IFloat, Shape: __ITextureShape, let isArray:int, let sampleCount:int, let isShadow:int, let format:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylod)]
 public vec2 textureQueryLod(__TextureImpl<T,
         Shape,
         isArray,
@@ -1464,6 +1559,7 @@ public vec2 textureQueryLod(__TextureImpl<T,
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(Sampler1D<vector<T,N>> sampler)
 {
     int width;
@@ -1474,6 +1570,7 @@ public int textureQueryLevels(Sampler1D<vector<T,N>> sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(Sampler2D<vector<T,N>> sampler)
 {
     vector<int,2> dim;
@@ -1484,6 +1581,7 @@ public int textureQueryLevels(Sampler2D<vector<T,N>> sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(Sampler3D<vector<T,N>> sampler)
 {
     vector<int,3> dim;
@@ -1494,6 +1592,7 @@ public int textureQueryLevels(Sampler3D<vector<T,N>> sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(SamplerCube<vector<T,N>> sampler)
 {
     vector<int,2> dim;
@@ -1504,6 +1603,7 @@ public int textureQueryLevels(SamplerCube<vector<T,N>> sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(Sampler1DArray<vector<T,N>> sampler)
 {
     vector<int,2> dim;
@@ -1514,6 +1614,7 @@ public int textureQueryLevels(Sampler1DArray<vector<T,N>> sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(Sampler2DArray<vector<T,N>> sampler)
 {
     vector<int,3> dim;
@@ -1524,6 +1625,7 @@ public int textureQueryLevels(Sampler2DArray<vector<T,N>> sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(SamplerCubeArray<vector<T,N>> sampler)
 {
     vector<int,3> dim;
@@ -1533,6 +1635,7 @@ public int textureQueryLevels(SamplerCubeArray<vector<T,N>> sampler)
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(sampler1DShadow sampler)
 {
     int dim;
@@ -1542,6 +1645,7 @@ public int textureQueryLevels(sampler1DShadow sampler)
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(sampler2DShadow sampler)
 {
     vector<int,2> dim;
@@ -1551,6 +1655,7 @@ public int textureQueryLevels(sampler2DShadow sampler)
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(samplerCubeShadow sampler)
 {
     vector<int,2> dim;
@@ -1560,6 +1665,7 @@ public int textureQueryLevels(samplerCubeShadow sampler)
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(sampler1DArrayShadow sampler)
 {
     vector<int,2> dim;
@@ -1569,6 +1675,7 @@ public int textureQueryLevels(sampler1DArrayShadow sampler)
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(sampler2DArrayShadow sampler)
 {
     vector<int,3> dim;
@@ -1578,6 +1685,7 @@ public int textureQueryLevels(sampler2DArrayShadow sampler)
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_querylevels)]
 public int textureQueryLevels(samplerCubeArrayShadow sampler)
 {
     vector<int,3> dim;
@@ -1592,6 +1700,7 @@ public int textureQueryLevels(samplerCubeArrayShadow sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int, let sampleCount:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, image_samples)]
 public int textureSamples(Sampler2DMS<vector<T,N>,sampleCount> sampler)
 {
     vector<int,2> dim;
@@ -1603,6 +1712,7 @@ public int textureSamples(Sampler2DMS<vector<T,N>,sampleCount> sampler)
 
 __generic<T:__BuiltinArithmeticType, let N:int, let sampleCount:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, image_samples)]
 public int textureSamples(Sampler2DMSArray<vector<T,N>,sampleCount> sampler)
 {
     vector<int,3> dim;
@@ -1622,6 +1732,7 @@ public int textureSamples(Sampler2DMSArray<vector<T,N>,sampleCount> sampler)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> texture(Sampler1D<vector<T,N>> sampler, float p)
 {
     return __vectorReshape<4>(sampler.Sample(p));
@@ -1629,6 +1740,7 @@ public vector<T,4> texture(Sampler1D<vector<T,N>> sampler, float p)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> texture(Sampler1D<vector<T,N>> sampler, float p, constexpr float bias)
 {
     return __vectorReshape<4>(sampler.SampleBias(p, bias));
@@ -1636,6 +1748,7 @@ public vector<T,4> texture(Sampler1D<vector<T,N>> sampler, float p, constexpr fl
 
 __generic<T:__BuiltinFloatingPointType, let N:int, Shape: __ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> texture(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -1653,6 +1766,7 @@ public vector<T,4> texture(__TextureImpl<
 
 __generic<T:__BuiltinFloatingPointType, let N:int, Shape: __ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> texture(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -1669,12 +1783,14 @@ public vector<T,4> texture(__TextureImpl<
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float texture(sampler1DShadow sampler, vec3 p)
 {
     return sampler.SampleCmp(p.x, p.z);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float texture(sampler1DShadow sampler, vec3 p, float bias)
 {
     // TODO: Need to apply bias
@@ -1682,24 +1798,28 @@ public float texture(sampler1DShadow sampler, vec3 p, float bias)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float texture(sampler2DShadow sampler, vec3 p)
 {
     return sampler.SampleCmp(p.xy, p.z);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float texture(sampler2DShadow sampler, vec3 p, float bias)
 {
     // TODO: Need to apply bias
     return sampler.SampleCmp(p.xy, p.z);
 }
 
+[require(glsl_hlsl_spirv, texture_shadowlod_cube)]
 [ForceInline]
 public float texture(samplerCubeShadow sampler, vec4 p)
 {
     return sampler.SampleCmp(p.xyz, p.w);
 }
 
+[require(glsl_hlsl_spirv, texture_shadowlod_cube)]
 [ForceInline]
 public float texture(samplerCubeShadow sampler, vec4 p, float bias)
 {
@@ -1708,12 +1828,14 @@ public float texture(samplerCubeShadow sampler, vec4 p, float bias)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float texture(sampler1DArrayShadow sampler, vec3 p)
 {
     return sampler.SampleCmp(p.xy, p.z);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float texture(sampler1DArrayShadow sampler, vec3 p, float bias)
 {
     // TODO: Need to apply bias
@@ -1721,12 +1843,14 @@ public float texture(sampler1DArrayShadow sampler, vec3 p, float bias)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float texture(sampler2DArrayShadow sampler, vec4 p)
 {
     return sampler.SampleCmp(p.xyz, p.w);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod_cube)]
 public float texture(samplerCubeArrayShadow sampler, vec4 p, float compare)
 {
     return sampler.SampleCmp(p, compare);
@@ -1738,6 +1862,7 @@ public float texture(samplerCubeArrayShadow sampler, vec4 p, float compare)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec2 p)
 {
     return texture(sampler, p.x / p.y);
@@ -1745,6 +1870,7 @@ public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec2 p)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec2 p, float bias)
 {
     return texture(sampler, p.x / p.y, bias);
@@ -1752,6 +1878,7 @@ public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec2 p, float bia
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec4 p)
 {
     return texture(sampler, p.x / p.w);
@@ -1759,6 +1886,7 @@ public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec4 p)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec4 p, float bias)
 {
     return texture(sampler, p.x / p.w, bias);
@@ -1766,6 +1894,7 @@ public vector<T,4> textureProj(Sampler1D<vector<T,N>> sampler, vec4 p, float bia
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec3 p)
 {
     return texture(sampler, p.xy / p.z);
@@ -1773,6 +1902,7 @@ public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec3 p)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec3 p, float bias)
 {
     return texture(sampler, p.xy / p.z, bias);
@@ -1780,6 +1910,7 @@ public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec3 p, float bia
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec4 p)
 {
     return texture(sampler, p.xy / p.w);
@@ -1787,6 +1918,7 @@ public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec4 p)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec4 p, float bias)
 {
     return texture(sampler, p.xy / p.w, bias);
@@ -1794,6 +1926,7 @@ public vector<T,4> textureProj(Sampler2D<vector<T,N>> sampler, vec4 p, float bia
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler3D<vector<T,N>> sampler, vec4 p)
 {
     return texture(sampler, p.xyz / p.w);
@@ -1801,30 +1934,35 @@ public vector<T,4> textureProj(Sampler3D<vector<T,N>> sampler, vec4 p)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProj(Sampler3D<vector<T,N>> sampler, vec4 p, float bias)
 {
     return texture(sampler, p.xyz / p.w, bias);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProj(sampler1DShadow sampler, vec4 p)
 {
     return texture(sampler, p.xyz / p.w);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProj(sampler1DShadow sampler, vec4 p, float bias)
 {
     return texture(sampler, p.xyz / p.w, bias);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProj(sampler2DShadow sampler, vec4 p)
 {
     return texture(sampler, p.xyz / p.w);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProj(sampler2DShadow sampler, vec4 p, float bias)
 {
     return texture(sampler, p.xyz / p.w, bias);
@@ -1836,6 +1974,7 @@ public float textureProj(sampler2DShadow sampler, vec4 p, float bias)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureLod(Sampler1D<vector<T,N>> sampler, float p, float lod)
 {
     return __vectorReshape<4>(sampler.SampleLevel(p, lod));
@@ -1843,6 +1982,7 @@ public vector<T,4> textureLod(Sampler1D<vector<T,N>> sampler, float p, float lod
 
 __generic<T:__BuiltinFloatingPointType, let N:int, Shape: __ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureLod(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -1859,6 +1999,7 @@ public vector<T,4> textureLod(__TextureImpl<
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureLod(sampler2DShadow sampler, vec3 p, float lod)
 {
     // TODO: Need to apply lod
@@ -1866,6 +2007,7 @@ public float textureLod(sampler2DShadow sampler, vec3 p, float lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureLod(sampler1DShadow sampler, vec3 p, float lod)
 {
     // TODO: Need to apply lod
@@ -1873,6 +2015,7 @@ public float textureLod(sampler1DShadow sampler, vec3 p, float lod)
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureLod(sampler1DArrayShadow sampler, vec3 p, float lod)
 {
     // TODO: Need to apply lod
@@ -1885,6 +2028,7 @@ public float textureLod(sampler1DArrayShadow sampler, vec3 p, float lod)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureOffset(Sampler1D<vector<T,N>> sampler, float p, constexpr int offset, float bias = 0.0)
 {
     return __vectorReshape<4>(sampler.SampleBias(p, bias, offset));
@@ -1892,6 +2036,7 @@ public vector<T,4> textureOffset(Sampler1D<vector<T,N>> sampler, float p, conste
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureOffset(Sampler2D<vector<T,N>> sampler, vec2 p, constexpr ivec2 offset, float bias = 0.0)
 {
     return __vectorReshape<4>(sampler.SampleBias(p, bias, offset));
@@ -1899,12 +2044,14 @@ public vector<T,4> textureOffset(Sampler2D<vector<T,N>> sampler, vec2 p, constex
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureOffset(Sampler3D<vector<T,N>> sampler, vec3 p, constexpr ivec3 offset, float bias = 0.0)
 {
     return __vectorReshape<4>(sampler.SampleBias(p, bias, offset));
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureOffset(sampler2DShadow sampler, vec3 p, constexpr ivec2 offset, float bias = 0.0)
 {
     // TODO: Need to apply bias
@@ -1912,6 +2059,7 @@ public float textureOffset(sampler2DShadow sampler, vec3 p, constexpr ivec2 offs
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureOffset(sampler1DShadow sampler, vec3 p, constexpr int offset, float bias = 0.0)
 {
     // TODO: Need to apply bias
@@ -1920,6 +2068,7 @@ public float textureOffset(sampler1DShadow sampler, vec3 p, constexpr int offset
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureOffset(Sampler1DArray<vector<T,N>> sampler, vec2 p, constexpr int offset, float bias = 0.0)
 {
     return __vectorReshape<4>(sampler.SampleBias(p, bias, offset));
@@ -1927,12 +2076,14 @@ public vector<T,4> textureOffset(Sampler1DArray<vector<T,N>> sampler, vec2 p, co
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureOffset(Sampler2DArray<vector<T,N>> sampler, vec3 p, constexpr ivec2 offset, float bias = 0.0)
 {
     return __vectorReshape<4>(sampler.SampleBias(p, bias, offset));
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureOffset(sampler1DArrayShadow sampler, vec3 p, constexpr int offset, float bias = 0.0)
 {
     // TODO: Need to apply bias
@@ -1940,6 +2091,7 @@ public float textureOffset(sampler1DArrayShadow sampler, vec3 p, constexpr int o
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureOffset(sampler2DArrayShadow sampler, vec4 p, constexpr ivec2 offset)
 {
     return sampler.SampleCmp(p.xyz, p.w, offset);
@@ -1951,6 +2103,7 @@ public float textureOffset(sampler2DArrayShadow sampler, vec4 p, constexpr ivec2
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetch(Sampler1D<vector<T,N>> sampler, int p, int lod)
 {
     return __vectorReshape<4>(sampler.Load(int2(p, lod)));
@@ -1958,6 +2111,7 @@ public vector<T,4> texelFetch(Sampler1D<vector<T,N>> sampler, int p, int lod)
 
 __generic<T:__BuiltinArithmeticType, let N:int, Shape:__ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetch(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -1975,6 +2129,7 @@ public vector<T,4> texelFetch(__TextureImpl<
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetch(Sampler2DRect<vector<T,N>> sampler, ivec2 p)
 {
     return __vectorReshape<4>(sampler.Load(int3(p.xy,0)));
@@ -1982,6 +2137,7 @@ public vector<T,4> texelFetch(Sampler2DRect<vector<T,N>> sampler, ivec2 p)
 
 __generic<T:__BuiltinArithmeticType, let N:int, let format:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetch(SamplerBuffer<vector<T,N>,format> sampler, int p)
 {
     return __vectorReshape<4>(sampler.Load(p));
@@ -1989,6 +2145,7 @@ public vector<T,4> texelFetch(SamplerBuffer<vector<T,N>,format> sampler, int p)
 
 __generic<T:__BuiltinArithmeticType, let N:int, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetch(__TextureImpl<
         vector<T,N>,
         __Shape2D,
@@ -2010,6 +2167,7 @@ public vector<T,4> texelFetch(__TextureImpl<
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetchOffset(Sampler1D<vector<T,N>> sampler, int p, int lod, constexpr int offset)
 {
     return texelFetch(sampler, p + offset, lod);
@@ -2017,6 +2175,7 @@ public vector<T,4> texelFetchOffset(Sampler1D<vector<T,N>> sampler, int p, int l
 
 __generic<T:__BuiltinArithmeticType, let N:int, Shape:__ITextureShape, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetchOffset(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -2034,6 +2193,7 @@ public vector<T,4> texelFetchOffset(__TextureImpl<
 
 __generic<T:__BuiltinArithmeticType, let N:int, Shape:__ITextureShape, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetchOffset(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -2051,6 +2211,7 @@ public vector<T,4> texelFetchOffset(__TextureImpl<
 
 __generic<T:__BuiltinArithmeticType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_samplerless)]
 public vector<T,4> texelFetchOffset(Sampler2DRect<vector<T,N>> sampler, ivec2 p, constexpr ivec2 offset)
 {
     return texelFetch(sampler, p + offset);
@@ -2062,6 +2223,7 @@ public vector<T,4> texelFetchOffset(Sampler2DRect<vector<T,N>> sampler, ivec2 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjOffset(Sampler1D<vector<T,N>> sampler, vec2 p, constexpr int offset, float bias = 0.0)
 {
     return textureOffset(sampler, p.x / p.y, offset, bias);
@@ -2069,6 +2231,7 @@ public vector<T,4> textureProjOffset(Sampler1D<vector<T,N>> sampler, vec2 p, con
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjOffset(Sampler1D<vector<T,N>> sampler, vec4 p, constexpr int offset, float bias = 0.0)
 {
     return textureOffset(sampler, p.x / p.w, offset, bias);
@@ -2076,6 +2239,7 @@ public vector<T,4> textureProjOffset(Sampler1D<vector<T,N>> sampler, vec4 p, con
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjOffset(Sampler2D<vector<T,N>> sampler, vec3 p, constexpr ivec2 offset, float bias = 0.0)
 {
     return textureOffset(sampler, p.xy / p.z, offset, bias);
@@ -2083,6 +2247,7 @@ public vector<T,4> textureProjOffset(Sampler2D<vector<T,N>> sampler, vec3 p, con
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjOffset(Sampler2D<vector<T,N>> sampler, vec4 p, constexpr ivec2 offset, float bias = 0.0)
 {
     return textureOffset(sampler, p.xy / p.w, offset, bias);
@@ -2090,18 +2255,21 @@ public vector<T,4> textureProjOffset(Sampler2D<vector<T,N>> sampler, vec4 p, con
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjOffset(Sampler3D<vector<T,N>> sampler, vec4 p, constexpr ivec3 offset, float bias = 0.0)
 {
     return textureOffset(sampler, p.xyz / p.w, offset, bias);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjOffset(sampler1DShadow sampler, vec4 p, constexpr int offset, float bias = 0.0)
 {
     return textureOffset(sampler, p.xyz / p.w, offset, bias);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjOffset(sampler2DShadow sampler, vec4 p, constexpr ivec2 offset, float bias = 0.0)
 {
     return textureOffset(sampler, p.xyz / p.w, offset, bias);
@@ -2113,6 +2281,7 @@ public float textureProjOffset(sampler2DShadow sampler, vec4 p, constexpr ivec2
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureLodOffset(Sampler1D<vector<T,N>> sampler, float p, float lod, constexpr int offset)
 {
     return __vectorReshape<4>(sampler.SampleLevel(p, lod, offset));
@@ -2120,6 +2289,7 @@ public vector<T,4> textureLodOffset(Sampler1D<vector<T,N>> sampler, float p, flo
 
 __generic<T:__BuiltinFloatingPointType, let N:int, Shape:__ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureLodOffset(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -2136,6 +2306,7 @@ public vector<T,4> textureLodOffset(__TextureImpl<
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureLodOffset(sampler1DShadow sampler, vec3 p, float lod, constexpr int offset)
 {
     // TODO: Need to apply lod
@@ -2143,6 +2314,7 @@ public float textureLodOffset(sampler1DShadow sampler, vec3 p, float lod, conste
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureLodOffset(sampler2DShadow sampler, vec3 p, float lod, constexpr ivec2 offset)
 {
     // TODO: Need to apply lod
@@ -2150,6 +2322,7 @@ public float textureLodOffset(sampler2DShadow sampler, vec3 p, float lod, conste
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureLodOffset(sampler1DArrayShadow sampler, vec3 p, float lod, constexpr int offset)
 {
     // TODO: Need to apply lod
@@ -2162,6 +2335,7 @@ public float textureLodOffset(sampler1DArrayShadow sampler, vec3 p, float lod, c
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLod(Sampler1D<vector<T,N>> sampler, vec2 p, float lod)
 {
     return textureLod(sampler, p.x / p.y, lod);
@@ -2169,6 +2343,7 @@ public vector<T,4> textureProjLod(Sampler1D<vector<T,N>> sampler, vec2 p, float
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLod(Sampler1D<vector<T,N>> sampler, vec4 p, float lod)
 {
     return textureLod(sampler, p.x / p.w, lod);
@@ -2176,6 +2351,7 @@ public vector<T,4> textureProjLod(Sampler1D<vector<T,N>> sampler, vec4 p, float
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLod(Sampler2D<vector<T,N>> sampler, vec3 p, float lod)
 {
     return textureLod(sampler, p.xy / p.z, lod);
@@ -2183,6 +2359,7 @@ public vector<T,4> textureProjLod(Sampler2D<vector<T,N>> sampler, vec3 p, float
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLod(Sampler2D<vector<T,N>> sampler, vec4 p, float lod)
 {
     return textureLod(sampler, p.xy / p.w, lod);
@@ -2190,18 +2367,21 @@ public vector<T,4> textureProjLod(Sampler2D<vector<T,N>> sampler, vec4 p, float
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLod(Sampler3D<vector<T,N>> sampler, vec4 p, float lod)
 {
     return textureLod(sampler, p.xyz / p.w, lod);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjLod(sampler1DShadow sampler, vec4 p, float lod)
 {
     return textureLod(sampler, p.xyz / p.w, lod);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjLod(sampler2DShadow sampler, vec4 p, float lod)
 {
     return textureLod(sampler, p.xyz / p.w, lod);
@@ -2213,6 +2393,7 @@ public float textureProjLod(sampler2DShadow sampler, vec4 p, float lod)
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLodOffset(Sampler1D<vector<T,N>> sampler, vec2 p, float lod, constexpr int offset)
 {
     return textureLodOffset(sampler, p.x / p.y, lod, offset);
@@ -2220,6 +2401,7 @@ public vector<T,4> textureProjLodOffset(Sampler1D<vector<T,N>> sampler, vec2 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLodOffset(Sampler1D<vector<T,N>> sampler, vec4 p, float lod, constexpr int offset)
 {
     return textureLodOffset(sampler, p.x / p.w, lod, offset);
@@ -2227,6 +2409,7 @@ public vector<T,4> textureProjLodOffset(Sampler1D<vector<T,N>> sampler, vec4 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLodOffset(Sampler2D<vector<T,N>> sampler, vec3 p, float lod, constexpr ivec2 offset)
 {
     return textureLodOffset(sampler, p.xy / p.z, lod, offset);
@@ -2234,6 +2417,7 @@ public vector<T,4> textureProjLodOffset(Sampler2D<vector<T,N>> sampler, vec3 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLodOffset(Sampler2D<vector<T,N>> sampler, vec4 p, float lod, constexpr ivec2 offset)
 {
     return textureLodOffset(sampler, p.xy / p.w, lod, offset);
@@ -2241,18 +2425,21 @@ public vector<T,4> textureProjLodOffset(Sampler2D<vector<T,N>> sampler, vec4 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vector<T,4> textureProjLodOffset(Sampler3D<vector<T,N>> sampler, vec4 p, float lod, constexpr ivec3 offset)
 {
     return textureLodOffset(sampler, p.xyz / p.w, lod, offset);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjLodOffset(sampler1DShadow sampler, vec4 p, float lod, constexpr int offset)
 {
     return textureLodOffset(sampler, p.xyz / p.w, lod, offset);
 }
 
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjLodOffset(sampler2DShadow sampler, vec4 p, float lod, constexpr ivec2 offset)
 {
     return textureLodOffset(sampler, p.xyz / p.w, lod, offset);
@@ -2262,8 +2449,10 @@ public float textureProjLodOffset(sampler2DShadow sampler, vec4 p, float lod, co
 // textureGrad
 // -------------------
 
+
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureGrad(Sampler1D<vector<T,N>> sampler, float p, float dPdx, float dPdy)
 {
     return __vectorReshape<4>(sampler.SampleGrad(p, dPdx, dPdy));
@@ -2271,6 +2460,7 @@ public vector<T,4> textureGrad(Sampler1D<vector<T,N>> sampler, float p, float dP
 
 __generic<T:__BuiltinFloatingPointType, let N:int, Shape:__ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureGrad(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -2287,6 +2477,7 @@ public vector<T,4> textureGrad(__TextureImpl<
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGrad(sampler1DShadow sampler, vec3 p, float dPdx, float dPdy)
 {
     // TODO: Not implemented
@@ -2294,6 +2485,7 @@ public float textureGrad(sampler1DShadow sampler, vec3 p, float dPdx, float dPdy
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGrad(sampler1DArrayShadow sampler, vec3 p, float dPdx, float dPdy)
 {
     // TODO: Not implemented
@@ -2301,6 +2493,7 @@ public float textureGrad(sampler1DArrayShadow sampler, vec3 p, float dPdx, float
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGrad(sampler2DShadow sampler, vec3 p, vec2 dPdx, vec2 dPdy)
 {
     // TODO: Not implemented on HLSL side yet.
@@ -2308,6 +2501,7 @@ public float textureGrad(sampler2DShadow sampler, vec3 p, vec2 dPdx, vec2 dPdy)
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_shadowlod_cube)]
 public float textureGrad(samplerCubeShadow sampler, vec4 p, vec3 dPdx, vec3 dPdy)
 {
     // TODO: Not implemented on HLSL side yet.
@@ -2315,6 +2509,7 @@ public float textureGrad(samplerCubeShadow sampler, vec4 p, vec3 dPdx, vec3 dPdy
 }
 
 [ForceInline]
+[require(cpp_cuda_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGrad(sampler2DArrayShadow sampler, vec4 p, vec2 dPdx, vec2 dPdy)
 {
     // TODO: Not implemented on HLSL side yet.
@@ -2327,12 +2522,14 @@ public float textureGrad(sampler2DArrayShadow sampler, vec4 p, vec2 dPdx, vec2 d
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureGradOffset(Sampler1D<vector<T,N>> sampler, float p, float dPdx, float dPdy, constexpr int offset)
 {
     return __vectorReshape<4>(sampler.SampleGrad(p, dPdx, dPdy, offset));
 }
 
 __generic<T:__BuiltinFloatingPointType, let N:int, Shape:__ITextureShape, let isArray:int, let sampleCount:int, let format:int>
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 [ForceInline]
 public vector<T,4> textureGradOffset(__TextureImpl<
         vector<T,N>,
@@ -2350,6 +2547,7 @@ public vector<T,4> textureGradOffset(__TextureImpl<
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGradOffset(sampler1DShadow sampler, vec3 p, float dPdx, float dPdy, constexpr int offset)
 {
     // TODO: Not implemented on HLSL side yet.
@@ -2357,6 +2555,7 @@ public float textureGradOffset(sampler1DShadow sampler, vec3 p, float dPdx, floa
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGradOffset(sampler2DShadow sampler, vec3 p, vec2 dPdx, vec2 dPdy, constexpr ivec2 offset)
 {
     // TODO: Not implemented on HLSL side yet.
@@ -2364,6 +2563,7 @@ public float textureGradOffset(sampler2DShadow sampler, vec3 p, vec2 dPdx, vec2
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGradOffset(sampler1DArrayShadow sampler, vec3 p, float dPdx, float dPdy, constexpr int offset)
 {
     // TODO: Not implemented on HLSL side yet.
@@ -2371,6 +2571,7 @@ public float textureGradOffset(sampler1DArrayShadow sampler, vec3 p, float dPdx,
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureGradOffset(sampler2DArrayShadow sampler, vec4 p, vec2 dPdx, vec2 dPdy, constexpr ivec2 offset)
 {
     // TODO: Not implemented on HLSL side yet.
@@ -2383,6 +2584,7 @@ public float textureGradOffset(sampler2DArrayShadow sampler, vec4 p, vec2 dPdx,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGrad(Sampler1D<vector<T,N>> sampler, vec2 p, float dPdx, float dPdy)
 {
     return textureGrad(sampler, p.x / p.y, dPdx, dPdy);
@@ -2390,6 +2592,7 @@ public vector<T,4> textureProjGrad(Sampler1D<vector<T,N>> sampler, vec2 p, float
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGrad(Sampler1D<vector<T,N>> sampler, vec4 p, float dPdx, float dPdy)
 {
     return textureGrad(sampler, p.x / p.w, dPdx, dPdy);
@@ -2397,6 +2600,7 @@ public vector<T,4> textureProjGrad(Sampler1D<vector<T,N>> sampler, vec4 p, float
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGrad(Sampler2D<vector<T,N>> sampler, vec3 p, vec2 dPdx, vec2 dPdy)
 {
     return textureGrad(sampler, p.xy / p.z, dPdx, dPdy);
@@ -2404,6 +2608,7 @@ public vector<T,4> textureProjGrad(Sampler2D<vector<T,N>> sampler, vec3 p, vec2
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGrad(Sampler2D<vector<T,N>> sampler, vec4 p, vec2 dPdx, vec2 dPdy)
 {
     return textureGrad(sampler, p.xy / p.w, dPdx, dPdy);
@@ -2411,18 +2616,21 @@ public vector<T,4> textureProjGrad(Sampler2D<vector<T,N>> sampler, vec4 p, vec2
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGrad(Sampler3D<vector<T,N>> sampler, vec4 p, vec3 dPdx, vec3 dPdy)
 {
     return textureGrad(sampler, p.xyz / p.w, dPdx, dPdy);
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjGrad(sampler1DShadow sampler, vec4 p, float dPdx, float dPdy)
 {
     return textureGrad(sampler, p.xyz / p.w, dPdx, dPdy);
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjGrad(sampler2DShadow sampler, vec4 p, vec2 dPdx, vec2 dPdy)
 {
     return textureGrad(sampler, p.xyz / p.w, dPdx, dPdy);
@@ -2434,6 +2642,7 @@ public float textureProjGrad(sampler2DShadow sampler, vec4 p, vec2 dPdx, vec2 dP
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGradOffset(Sampler1D<vector<T,N>> sampler, vec2 p, float dPdx, float dPdy, constexpr int offset)
 {
     return textureGradOffset(sampler, p.x / p.y, dPdx, dPdy, offset);
@@ -2441,6 +2650,7 @@ public vector<T,4> textureProjGradOffset(Sampler1D<vector<T,N>> sampler, vec2 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGradOffset(Sampler1D<vector<T,N>> sampler, vec4 p, float dPdx, float dPdy, constexpr int offset)
 {
     return textureGradOffset(sampler, p.x / p.w, dPdx, dPdy, offset);
@@ -2448,6 +2658,7 @@ public vector<T,4> textureProjGradOffset(Sampler1D<vector<T,N>> sampler, vec4 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGradOffset(Sampler2D<vector<T,N>> sampler, vec3 p, vec2 dPdx, vec2 dPdy, constexpr ivec2 offset)
 {
     return textureGradOffset(sampler, p.xy / p.z, dPdx, dPdy, offset);
@@ -2455,6 +2666,7 @@ public vector<T,4> textureProjGradOffset(Sampler2D<vector<T,N>> sampler, vec3 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGradOffset(Sampler2D<vector<T,N>> sampler, vec4 p, vec2 dPdx, vec2 dPdy, constexpr ivec2 offset)
 {
     return textureGradOffset(sampler, p.xy / p.w, dPdx, dPdy, offset);
@@ -2462,18 +2674,21 @@ public vector<T,4> textureProjGradOffset(Sampler2D<vector<T,N>> sampler, vec4 p,
 
 __generic<T:__BuiltinFloatingPointType, let N:int>
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1)]
 public vector<T,4> textureProjGradOffset(Sampler3D<vector<T,N>> sampler, vec4 p, vec3 dPdx, vec3 dPdy, constexpr ivec3 offset)
 {
     return textureGradOffset(sampler, p.xyz / p.w, dPdx, dPdy, offset);
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjGradOffset(sampler1DShadow sampler, vec4 p, float dPdx, float dPdy, constexpr int offset)
 {
     return textureGradOffset(sampler, p.xyz / p.w, dPdx, dPdy, offset);
 }
 
 [ForceInline]
+[require(cpp_glsl_hlsl_spirv, texture_shadowlod)]
 public float textureProjGradOffset(sampler2DShadow sampler, vec4 p, vec2 dPdx, vec2 dPdy, constexpr ivec2 offset)
 {
     return textureGradOffset(sampler, p.xyz / p.w, dPdx, dPdy, offset);
@@ -2489,6 +2704,7 @@ public float textureProjGradOffset(sampler2DShadow sampler, vec4 p, vec2 dPdx, v
 
 __generic<T:__BuiltinArithmeticType, let N:int, Shape:__ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_gather)]
 public vector<T,4> textureGather(__TextureImpl<
         vector<T,N>,
         Shape,
@@ -2512,6 +2728,7 @@ public vector<T,4> textureGather(__TextureImpl<
 
 __generic<Shape:__ITextureShape, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_gather)]
 public vec4 textureGather(__TextureImpl<
         float,
         Shape,
@@ -2533,6 +2750,7 @@ public vec4 textureGather(__TextureImpl<
 
 __generic<T:__BuiltinArithmeticType, let N:int, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_gather)]
 public vector<T,4> textureGatherOffset(__TextureImpl<
         vector<T,N>,
         __Shape2D,
@@ -2556,6 +2774,7 @@ public vector<T,4> textureGatherOffset(__TextureImpl<
 
 __generic<let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_gather)]
 public vec4 textureGatherOffset(__TextureImpl<
         float,
         __Shape2D,
@@ -2577,6 +2796,7 @@ public vec4 textureGatherOffset(__TextureImpl<
 
 __generic<T:__BuiltinArithmeticType, let N:int, let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_gather)]
 public vector<T,4> textureGatherOffsets(__TextureImpl<
         vector<T,N>,
         __Shape2D,
@@ -2600,6 +2820,7 @@ public vector<T,4> textureGatherOffsets(__TextureImpl<
 
 __generic<let isArray:int, let sampleCount:int, let format:int>
 [ForceInline]
+[require(glsl_hlsl_spirv, texture_gather)]
 public vec4 textureGatherOffsets(__TextureImpl<
         float,
         __Shape2D,
@@ -2619,196 +2840,235 @@ public vec4 textureGatherOffsets(__TextureImpl<
 // Section 8.9.5. Compatibility Profile Texture Functions
 //
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1D(sampler1D sampler, float coord)
 {
     return texture(sampler, coord);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1D(sampler1D sampler, float coord, float bias)
 {
     return texture(sampler, coord, bias);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1DProj(sampler1D sampler, vec2 coord)
 {
     return textureProj(sampler, coord);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1DProj(sampler1D sampler, vec2 coord, float bias)
 {
     return textureProj(sampler, coord, bias);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1DProj(sampler1D sampler, vec4 coord)
 {
     return textureProj(sampler, coord);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1DProj(sampler1D sampler, vec4 coord, float bias)
 {
     return textureProj(sampler, coord, bias);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1DLod(sampler1D sampler, float coord, float lod)
 {
     return textureLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1DProjLod(sampler1D sampler, vec2 coord, float lod)
 {
     return textureProjLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture1DProjLod(sampler1D sampler, vec4 coord, float lod)
 {
     return textureProjLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2D(sampler2D sampler, vec2 coord)
 {
     return texture(sampler, coord);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2D(sampler2D sampler, vec2 coord, float bias)
 {
     return texture(sampler, coord, bias);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2DProj(sampler2D sampler, vec3 coord)
 {
     return textureProj(sampler, coord);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2DProj(sampler2D sampler, vec3 coord, float bias)
 {
     return textureProj(sampler, coord, bias);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2DProj(sampler2D sampler, vec4 coord)
 {
     return textureProj(sampler, coord);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2DProj(sampler2D sampler, vec4 coord, float bias)
 {
     return textureProj(sampler, coord, bias);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2DLod(sampler2D sampler, vec2 coord, float lod)
 {
     return textureLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2DProjLod(sampler2D sampler, vec3 coord, float lod)
 {
     return textureProjLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture2DProjLod(sampler2D sampler, vec4 coord, float lod)
 {
     return textureProjLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture3D(sampler3D sampler, vec3 coord)
 {
     return texture(sampler, coord);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture3D(sampler3D sampler, vec3 coord, float bias)
 {
     return texture(sampler, coord, bias);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture3DProj(sampler3D sampler, vec4 coord)
 {
     return textureProj(sampler, coord);
 }
 
+[require(glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture3DProj(sampler3D sampler, vec4 coord, float bias)
 {
     return textureProj(sampler, coord, bias);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture3DLod(sampler3D sampler, vec3 coord, float lod)
 {
     return textureLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 texture3DProjLod(sampler3D sampler, vec4 coord, float lod)
 {
     return textureProjLod(sampler, coord, lod);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 textureCube(samplerCube sampler, vec3 coord)
 {
     return texture(sampler, coord);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 textureCube(samplerCube sampler, vec3 coord, float bias)
 {
     return texture(sampler, coord, bias);
 }
 
+[require(cpp_glsl_hlsl_spirv, texture_sm_4_1_fragment)]
 public vec4 textureCubeLod(samplerCube sampler, vec3 coord, float lod)
 {
     return textureLod(sampler, coord, lod);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow1D(sampler1DShadow sampler, vec3 coord)
 {
     return texture(sampler, coord);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow1D(sampler1DShadow sampler, vec3 coord, float bias)
 {
     return texture(sampler, coord, bias);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow2D(sampler2DShadow sampler, vec3 coord)
 {
     return texture(sampler, coord);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow2D(sampler2DShadow sampler, vec3 coord, float bias)
 {
     return texture(sampler, coord, bias);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow1DProj(sampler1DShadow sampler, vec4 coord)
 {
     return textureProj(sampler, coord);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow1DProj(sampler1DShadow sampler, vec4 coord, float bias)
 {
     return textureProj(sampler, coord, bias);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow2DProj(sampler2DShadow sampler, vec4 coord)
 {
     return textureProj(sampler, coord);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow2DProj(sampler2DShadow sampler, vec4 coord, float bias)
 {
     return textureProj(sampler, coord, bias);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow1DLod(sampler1DShadow sampler, vec3 coord, float lod)
 {
     return textureLod(sampler, coord, lod);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow2DLod(sampler2DShadow sampler, vec3 coord, float lod)
 {
     return textureLod(sampler, coord, lod);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow1DProjLod(sampler1DShadow sampler, vec4 coord, float lod)
 {
     return textureProjLod(sampler, coord, lod);
 }
 
+[require(glsl_spirv, texture_shadowlod)]
 public vec4 shadow2DProjLod(sampler2DShadow sampler, vec4 coord, float lod)
 {
     return textureProjLod(sampler, coord, lod);
@@ -3010,10 +3270,10 @@ ${{{{
 }}}}
 
         // readonly writeonly in GLSL means an object only allows information queries.
-        [require(spirv)]
-        [require(glsl)]
         [__readNone]
-        [ForceInline] public $(imageSizeIntOrIVec) imageSize(readonly writeonly $(fullTypeName) image)
+        [ForceInline]
+        [require(glsl_spirv, image_size)]
+        public $(imageSizeIntOrIVec) imageSize(readonly writeonly $(fullTypeName) image)
         {
             __target_switch
             {
@@ -3026,10 +3286,10 @@ ${{{{
                 };
             }
         }
-        [require(spirv)]
-        [require(glsl)]
         [__NoSideEffect]
-        [ForceInline] public $(targetType.prefix)vec4 imageLoad(readonly $(IMAGE_PARAMS))
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.prefix)vec4 imageLoad(readonly $(IMAGE_PARAMS))
         {
             __target_switch
             {
@@ -3044,9 +3304,9 @@ ${{{{
             }
             }
         }
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public void imageStore(writeonly $(IMAGE_PARAMS), $(targetType.prefix)vec4 data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public void imageStore(writeonly $(IMAGE_PARAMS), $(targetType.prefix)vec4 data)
         {
             __target_switch
             {
@@ -3067,10 +3327,10 @@ ${{{{
         {
 }}}}
             // readonly writeonly in GLSL means an object only allows information queries.
-            [require(spirv)]
-            [require(glsl)]
             [__readNone]
-            [ForceInline] public int imageSamples(readonly writeonly $(fullTypeName) image)
+            [ForceInline]
+            [require(glsl_spirv, image_samples)]
+            public int imageSamples(readonly writeonly $(fullTypeName) image)
             {
                 __target_switch
                 {
@@ -3086,9 +3346,9 @@ ${{{{
 ${{{{
         }
 }}}}
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicAdd($(IMAGE_PARAMS), $(targetType.type) data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicAdd($(IMAGE_PARAMS), $(targetType.type) data)
         {
             typeRequireChecks_image_atomic_tier1<$(targetType.type)>();
             __target_switch
@@ -3109,9 +3369,9 @@ ${{{{
             }
             }
         }
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicExchange($(IMAGE_PARAMS), $(targetType.type) data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicExchange($(IMAGE_PARAMS), $(targetType.type) data)
         {
             typeRequireChecks_image_atomic_tier1<$(targetType.type)>();
             __target_switch
@@ -3132,9 +3392,9 @@ ${{{{
             }
             }
         }
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicMin($(IMAGE_PARAMS), $(targetType.type) data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicMin($(IMAGE_PARAMS), $(targetType.type) data)
         {
             typeRequireChecks_image_atomic_tier2<$(targetType.type)>();
             __target_switch
@@ -3155,9 +3415,9 @@ ${{{{
             }
             }
         }
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicMax($(IMAGE_PARAMS), $(targetType.type) data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicMax($(IMAGE_PARAMS), $(targetType.type) data)
         {
             typeRequireChecks_image_atomic_tier2<$(targetType.type)>();
             __target_switch
@@ -3182,9 +3442,9 @@ ${{{{
         if (!targetType.isInt)
             continue;
 }}}}
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicAnd($(IMAGE_PARAMS), $(targetType.type) data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicAnd($(IMAGE_PARAMS), $(targetType.type) data)
         {
             __target_switch
             {
@@ -3204,9 +3464,9 @@ ${{{{
             }
             }
         }
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicOr($(IMAGE_PARAMS), $(targetType.type) data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicOr($(IMAGE_PARAMS), $(targetType.type) data)
         {
             __target_switch
             {
@@ -3226,9 +3486,10 @@ ${{{{
             }
             }
         }
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicXor($(IMAGE_PARAMS), $(targetType.type) data)
+        
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicXor($(IMAGE_PARAMS), $(targetType.type) data)
         {
             __target_switch
             {
@@ -3248,9 +3509,9 @@ ${{{{
             }
             }
         }
-        [require(spirv)]
-        [require(glsl)]
-        [ForceInline] public $(targetType.type) imageAtomicCompSwap($(IMAGE_PARAMS), $(targetType.type) compare, $(targetType.type) data)
+        [ForceInline]
+        [require(glsl_spirv, image_loadstore)]
+        public $(targetType.type) imageAtomicCompSwap($(IMAGE_PARAMS), $(targetType.type) compare, $(targetType.type) data)
         {
             __target_switch
             {
@@ -3287,6 +3548,7 @@ public typealias hitObjectNV = HitObject;
 
 //GL_EXT_ray_tracing BuiltIn's 
 
+[require(any_target, raytracing_allstages)]
 void requireGLSLExtForRayTracingBuiltin() 
 {
     __target_switch
@@ -3294,25 +3556,27 @@ void requireGLSLExtForRayTracingBuiltin()
     case glsl:
         __requireGLSLExtension("GL_EXT_ray_tracing");
         __intrinsic_asm "";
+    default:
+        return;
     }
 }
 
 __spirv_version(1.4) 
+[require(any_target, raytracing_allstages)]
 void setupExtForRayTracingBuiltIn() 
 {
     __target_switch
     {
     case glsl:
         requireGLSLExtForRayTracingBuiltin();
-    case spirv:
+    default:
         return;
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property uint3 gl_LaunchIDNV 
 {
+    [require(glsl_spirv, raytracing_allstages)]
     get 
     {
         setupExtForRayTracingBuiltIn();
@@ -3333,10 +3597,9 @@ public property uint3 gl_LaunchIDNV
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property uint3 gl_LaunchIDEXT 
 {
+    [require(cuda_glsl_hlsl_spirv, raytracing_allstages)]
     get 
     {
         setupExtForRayTracingBuiltIn();
@@ -3344,10 +3607,9 @@ public property uint3 gl_LaunchIDEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property uint3 gl_LaunchSizeNV 
 {
+    [require(glsl_spirv, raytracing_allstages)]
     get 
     {
         setupExtForRayTracingBuiltIn();
@@ -3368,10 +3630,9 @@ public property uint3 gl_LaunchSizeNV
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property uint3 gl_LaunchSizeEXT 
 {
+    [require(cuda_glsl_hlsl_spirv, raytracing_allstages)]
     get 
     {
         setupExtForRayTracingBuiltIn();
@@ -3379,10 +3640,10 @@ public property uint3 gl_LaunchSizeEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
+
 public property int gl_PrimitiveID 
 {
+    [require(cuda_glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get 
     {
         setupExtForRayTracingBuiltIn();
@@ -3390,10 +3651,9 @@ public property int gl_PrimitiveID
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property int gl_InstanceID 
 {
+    [require(cuda_glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get 
     {
         setupExtForRayTracingBuiltIn();
@@ -3401,10 +3661,9 @@ public property int gl_InstanceID
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property int gl_InstanceCustomIndexEXT 
 {
+    [require(cuda_glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get 
     {
         setupExtForRayTracingBuiltIn();
@@ -3412,10 +3671,9 @@ public property int gl_InstanceCustomIndexEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property int gl_GeometryIndexEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3423,10 +3681,9 @@ public property int gl_GeometryIndexEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property vec3 gl_WorldRayOriginEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection_miss)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3434,10 +3691,9 @@ public property vec3 gl_WorldRayOriginEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property vec3 gl_WorldRayDirectionEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection_miss)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3445,10 +3701,9 @@ public property vec3 gl_WorldRayDirectionEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property vec3 gl_ObjectRayOriginEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3456,10 +3711,9 @@ public property vec3 gl_ObjectRayOriginEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property vec3 gl_ObjectRayDirectionEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3467,10 +3721,9 @@ public property vec3 gl_ObjectRayDirectionEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property float gl_RayTminEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection_miss)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3478,10 +3731,9 @@ public property float gl_RayTminEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property float gl_RayTmaxEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection_miss)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3489,10 +3741,9 @@ public property float gl_RayTmaxEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property uint gl_IncomingRayFlagsEXT 
 {
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit_intersection_miss)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3500,10 +3751,9 @@ public property uint gl_IncomingRayFlagsEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property float gl_HitTEXT 
 {
+    [require(glsl_spirv, raytracing_anyhit_closesthit)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3524,10 +3774,10 @@ public property float gl_HitTEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property uint gl_HitKindEXT 
 {
+
+    [require(glsl_hlsl_spirv, raytracing_anyhit_closesthit)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3535,10 +3785,9 @@ public property uint gl_HitKindEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property mat4x3 gl_ObjectToWorldEXT 
 {
+    [require(glsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3560,10 +3809,9 @@ public property mat4x3 gl_ObjectToWorldEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property mat3x4 gl_ObjectToWorld3x4EXT 
 {
+    [require(glsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3584,10 +3832,9 @@ public property mat3x4 gl_ObjectToWorld3x4EXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property mat4x3 gl_WorldToObjectEXT 
 {
+    [require(glsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3609,10 +3856,9 @@ public property mat4x3 gl_WorldToObjectEXT
     }
 }
 
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
 public property mat3x4 gl_WorldToObject3x4EXT 
 {
+    [require(glsl_spirv, raytracing_anyhit_closesthit_intersection)]
     get
     {
         setupExtForRayTracingBuiltIn();
@@ -3635,9 +3881,8 @@ public property mat3x4 gl_WorldToObject3x4EXT
 
 // GL_EXT_ray_tracing functions
 
-__glsl_extension(GL_EXT_ray_query)
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
+__glsl_extension(GL_EXT_ray_tracing)
+[require(glsl_spirv, raytracing_raygen_closesthit_miss)]
 public void traceRayEXT(
     accelerationStructureEXT topLevel,
     uint rayFlags,
@@ -3689,17 +3934,15 @@ public void traceRayEXT(
     }
 }
 
-__glsl_extension(GL_EXT_ray_query)
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
+__glsl_extension(GL_EXT_ray_tracing)
+[require(glsl_spirv, raytracing_intersection)]
 public bool reportIntersectionEXT(float hitT, uint hitKind)
 {
     return __reportIntersection(hitT, hitKind);
 }
 
-__glsl_extension(GL_EXT_ray_query)
-[require(glsl, raytracing)]
-[require(spirv, raytracing)]
+__glsl_extension(GL_EXT_ray_tracing)
+[require(glsl_spirv, raytracing_raygen_closesthit_miss_callable)]
 public void executeCallableEXT(
     uint sbtRecordIndex, 
     int callable /*callableDataEXT and callableDataInEXT*/)
@@ -3748,9 +3991,8 @@ public static const uint gl_RayQueryCandidateIntersectionAABBEXT = 1U;
 // GL_EXT_ray_query functions
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public void rayQueryInitializeEXT(
     inout rayQueryEXT q,
     accelerationStructureEXT topLevel,
@@ -3765,17 +4007,15 @@ public void rayQueryInitializeEXT(
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public bool rayQueryProceedEXT(inout rayQueryEXT q)
 {
     return q.Proceed();
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
+[require(glsl_spirv, rayquery)]
 [mutating]
 [ForceInline]
 public void rayQueryTerminateEXT(inout rayQueryEXT q)
@@ -3784,28 +4024,25 @@ public void rayQueryTerminateEXT(inout rayQueryEXT q)
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public void rayQueryGenerateIntersectionEXT(inout rayQueryEXT q, float tHit)
 {
     q.CommitProceduralPrimitiveHit(tHit);
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public void rayQueryConfirmIntersectionEXT(inout rayQueryEXT q)
 {
     q.CommitNonOpaqueTriangleHit();
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public uint rayQueryGetIntersectionTypeEXT(rayQueryEXT q, bool committed)
 {
     if (committed)
@@ -3819,45 +4056,40 @@ public uint rayQueryGetIntersectionTypeEXT(rayQueryEXT q, bool committed)
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public float rayQueryGetRayTMinEXT(rayQueryEXT q)
 {
     return q.RayTMin();
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public uint rayQueryGetRayFlagsEXT(rayQueryEXT q)
 {
     return q.RayFlags();
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public vec3 rayQueryGetWorldRayOriginEXT(rayQueryEXT q)
 {
     return q.WorldRayOrigin();
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public vec3 rayQueryGetWorldRayDirectionEXT(rayQueryEXT q)
 {
     return q.WorldRayDirection();
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public float rayQueryGetIntersectionTEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3871,9 +4103,8 @@ public float rayQueryGetIntersectionTEXT(rayQueryEXT q, bool committed)
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public int rayQueryGetIntersectionInstanceCustomIndexEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3887,9 +4118,8 @@ public int rayQueryGetIntersectionInstanceCustomIndexEXT(rayQueryEXT q, bool com
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public int rayQueryGetIntersectionInstanceIdEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3903,9 +4133,8 @@ public int rayQueryGetIntersectionInstanceIdEXT(rayQueryEXT q, bool committed)
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public uint rayQueryGetIntersectionInstanceShaderBindingTableRecordOffsetEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3919,9 +4148,8 @@ public uint rayQueryGetIntersectionInstanceShaderBindingTableRecordOffsetEXT(ray
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public int rayQueryGetIntersectionGeometryIndexEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3935,9 +4163,8 @@ public int rayQueryGetIntersectionGeometryIndexEXT(rayQueryEXT q, bool committed
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public int rayQueryGetIntersectionPrimitiveIndexEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3951,9 +4178,8 @@ public int rayQueryGetIntersectionPrimitiveIndexEXT(rayQueryEXT q, bool committe
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public vec2 rayQueryGetIntersectionBarycentricsEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3967,9 +4193,8 @@ public vec2 rayQueryGetIntersectionBarycentricsEXT(rayQueryEXT q, bool committed
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public bool rayQueryGetIntersectionFrontFaceEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -3983,17 +4208,15 @@ public bool rayQueryGetIntersectionFrontFaceEXT(rayQueryEXT q, bool committed)
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public bool rayQueryGetIntersectionCandidateAABBOpaqueEXT(rayQueryEXT q) 
 {
     return q.CandidateProceduralPrimitiveNonOpaque();
 }
 
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public vec3 rayQueryGetIntersectionObjectRayDirectionEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -4007,9 +4230,8 @@ public vec3 rayQueryGetIntersectionObjectRayDirectionEXT(rayQueryEXT q, bool com
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public vec3 rayQueryGetIntersectionObjectRayOriginEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -4023,9 +4245,8 @@ public vec3 rayQueryGetIntersectionObjectRayOriginEXT(rayQueryEXT q, bool commit
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public mat4x3 rayQueryGetIntersectionObjectToWorldEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -4039,9 +4260,8 @@ public mat4x3 rayQueryGetIntersectionObjectToWorldEXT(rayQueryEXT q, bool commit
 }
 
 __glsl_extension(GL_EXT_ray_query)
-[require(glsl, rayquery)]
-[require(spirv, rayquery)]
 [ForceInline]
+[require(glsl_spirv, rayquery)]
 public mat4x3 rayQueryGetIntersectionWorldToObjectEXT(rayQueryEXT q, bool committed) 
 {
     if (committed) 
@@ -4059,9 +4279,8 @@ public mat4x3 rayQueryGetIntersectionWorldToObjectEXT(rayQueryEXT q, bool commit
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public void hitObjectTraceRayNV(
     inout hitObjectNV hitObject,
     accelerationStructureEXT topLevel,
@@ -4120,9 +4339,8 @@ __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
 __glsl_extension(GL_NV_ray_tracing_motion_blur)
-[require(glsl, ser_motion)]
-[require(spirv, ser_motion)]
 [ForceInline]
+[require(glsl_spirv, ser_motion_raygen_closesthit_miss)]
 public void hitObjectTraceRayMotionNV(
     inout hitObjectNV hitObject, 
     accelerationStructureEXT topLevel,
@@ -4185,9 +4403,8 @@ public void hitObjectTraceRayMotionNV(
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public void hitObjectRecordHitNV(
     inout hitObjectNV hitObject,
     accelerationStructureEXT topLevel,
@@ -4249,9 +4466,8 @@ __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
 __glsl_extension(GL_NV_ray_tracing_motion_blur)
-[require(glsl, ser_motion)]
-[require(spirv, ser_motion)]
 [ForceInline]
+[require(glsl_spirv, ser_motion_raygen_closesthit_miss)]
 public void hitObjectRecordHitMotionNV(
     inout hitObjectNV hitObject,
     accelerationStructureEXT topLevel,
@@ -4315,9 +4531,8 @@ public void hitObjectRecordHitMotionNV(
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public void hitObjectRecordHitWithIndexNV(
     inout hitObjectNV hitObject,
     accelerationStructureEXT topLevel,
@@ -4376,9 +4591,8 @@ __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
 __glsl_extension(GL_NV_ray_tracing_motion_blur)
-[require(glsl, ser_motion)]
-[require(spirv, ser_motion)]
 [ForceInline]
+[require(glsl_spirv, ser_motion_raygen_closesthit_miss)]
 public void hitObjectRecordHitWithIndexMotionNV(
     inout hitObjectNV hitObject,
     accelerationStructureEXT topLevel,
@@ -4441,9 +4655,8 @@ public void hitObjectRecordHitWithIndexMotionNV(
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public void hitObjectRecordMissNV(
     inout hitObjectNV hitObject, 
     uint sbtRecordIndex, 
@@ -4462,9 +4675,8 @@ __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
 __glsl_extension(GL_NV_ray_tracing_motion_blur)
-[require(glsl, ser_motion)]
-[require(spirv, ser_motion)]
 [ForceInline]
+[require(glsl_spirv, ser_motion_raygen_closesthit_miss)]
 public void hitObjectRecordMissMotionNV(
     inout hitObjectNV hitObject, 
     uint sbtRecordIndex, 
@@ -4484,9 +4696,8 @@ public void hitObjectRecordMissMotionNV(
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public void hitObjectRecordEmptyNV(hitObjectNV hitObject)
 {
     hitObject = HitObject::MakeNop();
@@ -4495,9 +4706,8 @@ public void hitObjectRecordEmptyNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public void hitObjectExecuteShaderNV(
     inout hitObjectNV hitObject, 
     constexpr int payload)
@@ -4521,9 +4731,8 @@ public void hitObjectExecuteShaderNV(
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public bool hitObjectIsEmptyNV(hitObjectNV hitObject)
 {
     return hitObject.IsNop();
@@ -4532,9 +4741,8 @@ public bool hitObjectIsEmptyNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public bool hitObjectIsMissNV(hitObjectNV hitObject)
 {
     return hitObject.IsMiss();
@@ -4543,9 +4751,8 @@ public bool hitObjectIsMissNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public bool hitObjectIsHitNV(hitObjectNV hitObject)
 {
     return hitObject.IsHit();
@@ -4554,9 +4761,8 @@ public bool hitObjectIsHitNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public float hitObjectGetRayTMinNV(hitObjectNV hitObject)
 {
     return hitObject.GetRayDesc().TMin;  
@@ -4565,9 +4771,8 @@ public float hitObjectGetRayTMinNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public float hitObjectGetRayTMaxNV(hitObjectNV hitObject)
 {
     return hitObject.GetRayDesc().TMax; 
@@ -4576,9 +4781,8 @@ public float hitObjectGetRayTMaxNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public vec3 hitObjectGetWorldRayOriginNV(hitObjectNV hitObject)
 {
     return hitObject.GetRayDesc().Origin;
@@ -4587,9 +4791,8 @@ public vec3 hitObjectGetWorldRayOriginNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public vec3 hitObjectGetWorldRayDirectionNV(hitObjectNV hitObject)
 {
     return hitObject.GetRayDesc().Direction; 
@@ -4598,9 +4801,8 @@ public vec3 hitObjectGetWorldRayDirectionNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public vec3 hitObjectGetObjectRayOriginNV(hitObjectNV hitObject)
 {
     return hitObject.GetObjectRayOrigin();
@@ -4609,9 +4811,8 @@ public vec3 hitObjectGetObjectRayOriginNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public vec3 hitObjectGetObjectRayDirectionNV(hitObjectNV hitObject)
 {
     return hitObject.GetObjectRayDirection();
@@ -4620,9 +4821,8 @@ public vec3 hitObjectGetObjectRayDirectionNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public mat4x3 hitObjectGetObjectToWorldNV(hitObjectNV hitObject)
 {
     return transpose(hitObject.GetObjectToWorld());
@@ -4631,9 +4831,8 @@ public mat4x3 hitObjectGetObjectToWorldNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public mat4x3 hitObjectGetWorldToObjectNV(hitObjectNV hitObject)
 {
     return transpose(hitObject.GetWorldToObject()); 
@@ -4642,9 +4841,8 @@ public mat4x3 hitObjectGetWorldToObjectNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public int hitObjectGetInstanceCustomIndexNV(hitObjectNV hitObject)
 {
     return hitObject.GetInstanceID();
@@ -4653,17 +4851,18 @@ public int hitObjectGetInstanceCustomIndexNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public int hitObjectGetInstanceIdNV(hitObjectNV hitObject)
 {
     return hitObject.GetInstanceIndex();
 }
 
-[require(glsl, ser)]
-[require(spirv, ser)]
+__glsl_extension(GL_EXT_ray_tracing)
+__glsl_extension(GL_NV_shader_invocation_reorder)
+__glsl_extension(GLSL_EXT_buffer_reference_uvec2)
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public int hitObjectGetGeometryIndexNV(hitObjectNV hitObject)
 {
     return hitObject.GetGeometryIndex();
@@ -4672,9 +4871,8 @@ public int hitObjectGetGeometryIndexNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public int hitObjectGetPrimitiveIndexNV(hitObjectNV hitObject)
 {
     return hitObject.GetPrimitiveIndex();
@@ -4683,9 +4881,8 @@ public int hitObjectGetPrimitiveIndexNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public uint hitObjectGetHitKindNV(hitObjectNV hitObject)
 {
     return hitObject.GetHitKind();
@@ -4694,9 +4891,8 @@ public uint hitObjectGetHitKindNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public void hitObjectGetAttributesNV(
     inout hitObjectNV hitObject, 
     constexpr int attributeLocation)
@@ -4721,9 +4917,8 @@ public void hitObjectGetAttributesNV(
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public uvec2 hitObjectGetShaderRecordBufferHandleNV(hitObjectNV hitObject)
 {
     return hitObject.GetShaderRecordBufferHandle();
@@ -4732,9 +4927,8 @@ public uvec2 hitObjectGetShaderRecordBufferHandleNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public uint hitObjectGetShaderBindingTableRecordIndexNV(hitObjectNV hitObject)
 {
     return hitObject.GetShaderTableIndex();
@@ -4743,9 +4937,8 @@ public uint hitObjectGetShaderBindingTableRecordIndexNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen_closesthit_miss)]
 public float hitObjectGetCurrentTimeNV(hitObjectNV hitObject)
 {
     return hitObject.GetCurrentTime();
@@ -4754,9 +4947,8 @@ public float hitObjectGetCurrentTimeNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen)]
 public void reorderThreadNV(uint hint, uint bits)
 {
     ReorderThread(hint, bits);
@@ -4765,9 +4957,8 @@ public void reorderThreadNV(uint hint, uint bits)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen)]
 public void reorderThreadNV(hitObjectNV hitObject)
 {
     ReorderThread(hitObject);
@@ -4776,9 +4967,8 @@ public void reorderThreadNV(hitObjectNV hitObject)
 __glsl_extension(GL_EXT_ray_tracing)
 __glsl_extension(GL_NV_shader_invocation_reorder)
 __glsl_extension(GLSL_EXT_buffer_reference_uvec2)
-[require(glsl, ser)]
-[require(spirv, ser)]
 [ForceInline]
+[require(glsl_spirv, ser_raygen)]
 public void reorderThreadNV(hitObjectNV hitObject, uint hint, uint bits)
 {
     ReorderThread(hitObject, hint, bits);
@@ -4786,10 +4976,9 @@ public void reorderThreadNV(hitObjectNV hitObject, uint hint, uint bits)
 
 /// GL_NV_ray_tracing_motion_blur
 
-[require(glsl, raytracing_motionblur)]
-[require(spirv, raytracing_motionblur)]
 public property float gl_CurrentRayTimeNV
 {
+    [require(glsl_spirv, raytracing_motionblur_anyhit_closesthit_intersection_miss)]
     get
     {
         __target_switch
@@ -4809,9 +4998,8 @@ public property float gl_CurrentRayTimeNV
 
 __glsl_extension(GL_EXT_ray_tracing) 
 __glsl_extension(GL_NV_ray_tracing_motion_blur)
-[require(glsl, raytracing_motionblur)]
-[require(spirv, raytracing_motionblur)]
 [ForceInline]
+[require(glsl_spirv, raytracing_motionblur_raygen_closesthit_miss)]
 public void traceRayMotionNV(
     accelerationStructureEXT topLevel,
     uint rayFlags,
@@ -4901,7 +5089,7 @@ void shader_subgroup_preamble() {
     {
     case glsl:
         typeRequireChecks_shader_subgroup_GLSL<T>();
-    case spirv:
+    default:
         return;
     }
 
@@ -4909,50 +5097,57 @@ void shader_subgroup_preamble() {
 
 // GL_KHR_shader_subgroup_basic Built-in Variables
 
+[require(cpp_cuda_glsl_hlsl_spirv, subgroup_basic)]
 void requireGLSLExtForSubgroupBasicBuiltin() {
     __target_switch
     {
     case glsl:
         __requireGLSLExtension("GL_KHR_shader_subgroup_basic");
         __intrinsic_asm "";
+    default:
+        return;
     }
 }
 
-__spirv_version(1.3) 
+[require(cpp_cuda_glsl_hlsl_spirv, subgroup_basic)]
 void setupExtForSubgroupBasicBuiltIn() {
     __target_switch
     {
     case glsl:
         requireGLSLExtForSubgroupBasicBuiltin();
-    case spirv:
+    default:
         return;
     }
 }
 
+__spirv_version(1.3)
+[require(cpp_cuda_glsl_hlsl_spirv, subgroup_ballot)]
 void requireGLSLExtForSubgroupBallotBuiltin() {
     __target_switch
     {
     case glsl:
         __requireGLSLExtension("GL_KHR_shader_subgroup_ballot");
         __intrinsic_asm "";
+    default:
+        return;
     }
 }
 
-__spirv_version(1.3) 
+__spirv_version(1.3)
+[require(cpp_cuda_glsl_hlsl_spirv, subgroup_ballot)]
 void setupExtForSubgroupBallotBuiltIn() {
     __target_switch
     {
     case glsl:
         requireGLSLExtForSubgroupBallotBuiltin();
-    case spirv:
+    default:
         return;
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uint gl_NumSubgroups {
     
+    [require(glsl_spirv, subgroup_basic)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         __target_switch
@@ -4969,10 +5164,9 @@ public property uint gl_NumSubgroups {
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uint gl_SubgroupID
 {
+    [require(glsl_spirv, subgroup_basic)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         __target_switch
@@ -4988,30 +5182,27 @@ public property uint gl_SubgroupID
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uint gl_SubgroupSize
 {
+    [require(cpp_cuda_glsl_hlsl_spirv, subgroup_basic)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         return WaveGetLaneCount();
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uint gl_SubgroupInvocationID
 {
+    [require(cpp_cuda_glsl_hlsl_spirv, subgroup_basic)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         return WaveGetLaneIndex();
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uvec4 gl_SubgroupEqMask
 {
+    [require(glsl_spirv, subgroup_basic_ballot)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         setupExtForSubgroupBallotBuiltIn();
@@ -5028,10 +5219,9 @@ public property uvec4 gl_SubgroupEqMask
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uvec4 gl_SubgroupGeMask
 {
+    [require(glsl_spirv, subgroup_basic_ballot)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         setupExtForSubgroupBallotBuiltIn();
@@ -5048,10 +5238,9 @@ public property uvec4 gl_SubgroupGeMask
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uvec4 gl_SubgroupGtMask
 {
+    [require(glsl_spirv, subgroup_basic_ballot)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         setupExtForSubgroupBallotBuiltIn();
@@ -5068,10 +5257,9 @@ public property uvec4 gl_SubgroupGtMask
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uvec4 gl_SubgroupLeMask
 {
+    [require(glsl_spirv, subgroup_basic_ballot)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         setupExtForSubgroupBallotBuiltIn();
@@ -5088,10 +5276,9 @@ public property uvec4 gl_SubgroupLeMask
     }
 }
 
-[require(glsl)]
-[require(spirv)]
 public property uvec4 gl_SubgroupLtMask
 {
+    [require(glsl_spirv, subgroup_basic_ballot)]
     get {
         setupExtForSubgroupBasicBuiltIn();
         setupExtForSubgroupBallotBuiltIn();
@@ -5110,9 +5297,11 @@ public property uvec4 gl_SubgroupLtMask
 
 // GL_KHR_shader_subgroup_basic
 
-__glsl_extension(GL_KHR_shader_subgroup_basic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public void subgroupBarrier()
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_basic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_basic)]
+public void subgroupBarrier()
 {
     __target_switch
     {
@@ -5131,9 +5320,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_basic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public void subgroupMemoryBarrier()
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_basic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_basic)]
+public void subgroupMemoryBarrier()
 {
     __target_switch
     {
@@ -5152,9 +5343,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_basic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public void subgroupMemoryBarrierBuffer()
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_basic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_basic)]
+public void subgroupMemoryBarrierBuffer()
 {
     // the following implementation is NOT the same as DeviceMemoryBarrier
     // HLSL lacks the same granularity of blocking on subgroup memory within a subgroup
@@ -5175,9 +5368,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_basic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public void subgroupMemoryBarrierImage()
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_basic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_basic)]
+public void subgroupMemoryBarrierImage()
 {
     __target_switch
     {
@@ -5195,9 +5390,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_basic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public void subgroupMemoryBarrierShared()
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_basic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_basic)]
+public void subgroupMemoryBarrierShared()
 {
     __target_switch
     {
@@ -5217,9 +5414,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_basic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public bool subgroupElect()
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_basic) 
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_basic)]
+public bool subgroupElect()
 {
     __target_switch
     {
@@ -5235,36 +5434,41 @@ __spirv_version(1.3) [require(spirv)]
 
 // GL_KHR_shader_subgroup_vote
 
-__glsl_extension(GL_KHR_shader_subgroup_vote) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public bool subgroupAll(bool value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_vote)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_vote)]
+public bool subgroupAll(bool value)
 {
-
     return WaveActiveAllTrue(value);
-
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_vote) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public bool subgroupAny(bool value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_vote)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_vote)]
+public bool subgroupAny(bool value)
 {
     return WaveActiveAnyTrue(value);
-    
 }
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_vote) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public bool subgroupAllEqual(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_vote)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_vote)]
+public bool subgroupAllEqual(T value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveAllEqual(value);
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_vote) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public bool subgroupAllEqual(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_vote)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_vote)]
+public bool subgroupAllEqual(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveAllEqual(value);
@@ -5273,45 +5477,55 @@ __spirv_version(1.3) [require(spirv)]
 // GL_KHR_shader_subgroup_arithmetic
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupAdd(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public T subgroupAdd(T value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveSum(value);
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupMul(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public T subgroupMul(T value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveProduct(value);
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupMin(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public T subgroupMin(T value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveMin(value);
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupMax(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public T subgroupMax(T value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveMax(value);
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupAnd(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupAnd(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5334,9 +5548,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupOr(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupOr(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5359,9 +5575,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupXor(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupXor(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5384,9 +5602,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupInclusiveAdd(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupInclusiveAdd(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5403,9 +5623,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupInclusiveMul(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupInclusiveMul(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5422,9 +5644,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupInclusiveMin(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupInclusiveMin(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5443,9 +5667,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupInclusiveMax(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupInclusiveMax(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5464,9 +5690,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupInclusiveAnd(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupInclusiveAnd(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5489,9 +5717,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupInclusiveOr(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupInclusiveOr(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5514,9 +5744,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupInclusiveXor(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupInclusiveXor(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5531,9 +5763,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupExclusiveAdd(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public T subgroupExclusiveAdd(T value)
 {
     shader_subgroup_preamble<T>();
     return WavePrefixSum(value);
@@ -5541,18 +5775,22 @@ __spirv_version(1.3) [require(spirv)]
 
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupExclusiveMul(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public T subgroupExclusiveMul(T value)
 {
     shader_subgroup_preamble<T>();
     return WavePrefixProduct(value);
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupExclusiveMin(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupExclusiveMin(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5571,9 +5809,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupExclusiveMax(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupExclusiveMax(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5592,9 +5832,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupExclusiveAnd(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupExclusiveAnd(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5607,9 +5849,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupExclusiveOr(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupExclusiveOr(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5622,9 +5866,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupExclusiveXor(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public T subgroupExclusiveXor(T value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5640,45 +5886,55 @@ __spirv_version(1.3) [require(spirv)]
 //note: this is a seperate section because it is so huge that the only reasonable way to implement this is to just regex replace code
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupAdd(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupAdd(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveSum(value);
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupMul(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupMul(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveProduct(value);
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupMin(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupMin(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveMin(value);
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupMax(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupMax(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WaveActiveMax(value);
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupAnd(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupAnd(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5702,9 +5958,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupOr(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupOr(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5728,9 +5986,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupXor(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupXor(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5753,9 +6013,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupInclusiveAdd(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupInclusiveAdd(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5772,9 +6034,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupInclusiveMul(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupInclusiveMul(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5791,9 +6055,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupInclusiveMin(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupInclusiveMin(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5812,9 +6078,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupInclusiveMax(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupInclusiveMax(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5833,9 +6101,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupInclusiveAnd(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupInclusiveAnd(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5849,9 +6119,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupInclusiveOr(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupInclusiveOr(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5865,9 +6137,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupInclusiveXor(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupInclusiveXor(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5881,9 +6155,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupExclusiveAdd(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupExclusiveAdd(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WavePrefixSum(value);
@@ -5891,18 +6167,22 @@ __spirv_version(1.3) [require(spirv)]
 
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupExclusiveMul(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupExclusiveMul(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WavePrefixProduct(value);
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupExclusiveMin(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupExclusiveMin(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5921,9 +6201,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupExclusiveMax(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupExclusiveMax(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5942,9 +6224,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupExclusiveAnd(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupExclusiveAnd(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5957,9 +6241,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupExclusiveOr(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupExclusiveOr(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5972,9 +6258,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_arithmetic) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupExclusiveXor(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_arithmetic)
+[ForceInline]
+[require(glsl_spirv, subgroup_arithmetic)]
+public vector<T,N> subgroupExclusiveXor(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -5989,45 +6277,55 @@ __spirv_version(1.3) [require(spirv)]
 // GL_KHR_shader_subgroup_ballot
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupBroadcast(T value, uint id)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_ballot)]
+public T subgroupBroadcast(T value, uint id)
 {
     shader_subgroup_preamble<T>();
     return WaveMaskBroadcastLaneAt(WaveGetActiveMask(), value, id);
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupBroadcast(vector<T,N> value, uint id)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_ballot)]
+public vector<T,N> subgroupBroadcast(vector<T,N> value, uint id)
 {
     shader_subgroup_preamble<T>();
     return WaveMaskBroadcastLaneAt(WaveGetActiveMask(), value, id);
 }
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupBroadcastFirst(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_ballot)]
+public T subgroupBroadcastFirst(T value)
 {
     shader_subgroup_preamble<T>();
     return WaveMaskReadLaneFirst(WaveGetActiveMask(), value);
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupBroadcastFirst(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_ballot)]
+public vector<T,N> subgroupBroadcastFirst(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return WaveMaskReadLaneFirst(WaveGetActiveMask(), value);
 }
 
 // WaveMaskBallot is not the same; it force trunc's
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public uvec4 subgroupBallot(bool value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_ballot)]
+public uvec4 subgroupBallot(bool value)
 {
     return WaveActiveBallot(value);
 }
@@ -6042,9 +6340,11 @@ __spirv_version(1.3) [require(spirv)]
 // note 2: we have a waveLaneCount check because based on wave lane count we can determine if we can do a 
 // fast path or slow path (know index is 0 or non 0)
 // }
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public bool subgroupInverseBallot(uvec4 value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_ballot)]
+public bool subgroupInverseBallot(uvec4 value)
 {
     __target_switch
     {
@@ -6075,9 +6375,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 // same logic as subgroupInverseBallot
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public bool subgroupBallotBitExtract(uvec4 value, uint index)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_ballot)]
+public bool subgroupBallotBitExtract(uvec4 value, uint index)
 {
     __target_switch
     {
@@ -6107,9 +6409,11 @@ __spirv_version(1.3) [require(spirv)]
 
 
 // the count is only supposed to use uvec4 values within bottom bits of subgroup launched, not a simple countbits
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public uint subgroupBallotBitCount(uvec4 value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(glsl_spirv, subgroup_ballot)]
+public uint subgroupBallotBitCount(uvec4 value)
 {
     __target_switch
     {
@@ -6123,9 +6427,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public uint subgroupBallotInclusiveBitCount(uvec4 value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(glsl_spirv, subgroup_ballot)]
+public uint subgroupBallotInclusiveBitCount(uvec4 value)
 {
     __target_switch
     {
@@ -6139,9 +6445,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public uint subgroupBallotExclusiveBitCount(uvec4 value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(glsl_spirv, subgroup_ballot)]
+public uint subgroupBallotExclusiveBitCount(uvec4 value)
 {
     __target_switch
     {
@@ -6155,9 +6463,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public uint subgroupBallotFindLSB(uvec4 value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(glsl_spirv, subgroup_ballot)]
+public uint subgroupBallotFindLSB(uvec4 value)
 {
     __target_switch
     {
@@ -6171,9 +6481,11 @@ __spirv_version(1.3) [require(spirv)]
     }
 }
 
-__glsl_extension(GL_KHR_shader_subgroup_ballot) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public uint subgroupBallotFindMSB(uvec4 value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_ballot)
+[ForceInline]
+[require(glsl_spirv, subgroup_ballot)]
+public uint subgroupBallotFindMSB(uvec4 value)
 {
     __target_switch
     {
@@ -6190,17 +6502,20 @@ __spirv_version(1.3) [require(spirv)]
 // GL_KHR_shader_subgroup_shuffle
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupShuffle(T value, uint index)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_shuffle)]
+public T subgroupShuffle(T value, uint index)
 {
     shader_subgroup_preamble<T>();
     return WaveShuffle(value, index);
 }
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle)
+[require(glsl_spirv, subgroup_shuffle)]
 [ForceInline] public T subgroupShuffleXor(T value, uint mask)
 {
     shader_subgroup_preamble<T>();
@@ -6217,18 +6532,22 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupShuffle(vector<T,N> value, uint index)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle)
+[ForceInline]
+[require(cuda_glsl_hlsl_spirv, subgroup_shuffle)]
+public vector<T,N> subgroupShuffle(vector<T,N> value, uint index)
 {
     shader_subgroup_preamble<T>();
     return WaveShuffle(value, index);
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupShuffleXor(vector<T,N> value, uint mask)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle)
+[ForceInline]
+[require(glsl_spirv, subgroup_shuffle)]
+public vector<T,N> subgroupShuffleXor(vector<T,N> value, uint mask)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6247,9 +6566,11 @@ __spirv_version(1.3) [require(spirv)]
 // GL_KHR_shader_subgroup_shuffle_relative
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupShuffleUp(T value, uint delta)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative)
+[ForceInline]
+[require(glsl_spirv, subgroup_shufflerelative)]
+public T subgroupShuffleUp(T value, uint delta)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6265,9 +6586,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupShuffleDown(T value, uint delta)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative)
+[ForceInline]
+[require(glsl_spirv, subgroup_shufflerelative)]
+public T subgroupShuffleDown(T value, uint delta)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6284,9 +6607,11 @@ __spirv_version(1.3) [require(spirv)]
 
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupShuffleUp(vector<T,N> value, uint delta)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative)
+[ForceInline]
+[require(glsl_spirv, subgroup_shufflerelative)]
+public vector<T,N> subgroupShuffleUp(vector<T,N> value, uint delta)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6302,9 +6627,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupShuffleDown(vector<T,N> value, uint delta)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_shuffle_relative)
+[ForceInline]
+[require(glsl_spirv, subgroup_shufflerelative)]
+public vector<T,N> subgroupShuffleDown(vector<T,N> value, uint delta)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6321,9 +6648,11 @@ __spirv_version(1.3) [require(spirv)]
 // GL_KHR_shader_subgroup_clustered
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupClusteredAdd(T value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public T subgroupClusteredAdd(T value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6340,9 +6669,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupClusteredMul(T value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public T subgroupClusteredMul(T value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6359,9 +6690,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupClusteredMin(T value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public T subgroupClusteredMin(T value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6380,9 +6713,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupClusteredMax(T value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public T subgroupClusteredMax(T value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6401,9 +6736,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupClusteredAnd(T value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public T subgroupClusteredAnd(T value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6417,9 +6754,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupClusteredOr(T value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public T subgroupClusteredOr(T value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6435,9 +6774,11 @@ __spirv_version(1.3) [require(spirv)]
 
 
 __generic<T : __BuiltinLogicalType>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupClusteredXor(T value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public T subgroupClusteredXor(T value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6453,9 +6794,11 @@ __spirv_version(1.3) [require(spirv)]
 
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupClusteredAdd(vector<T,N> value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public vector<T,N> subgroupClusteredAdd(vector<T,N> value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6473,9 +6816,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupClusteredMul(vector<T,N> value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public vector<T,N> subgroupClusteredMul(vector<T,N> value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6492,9 +6837,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupClusteredMin(vector<T,N> value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public vector<T,N> subgroupClusteredMin(vector<T,N> value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6513,9 +6860,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinArithmeticType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupClusteredMax(vector<T,N> value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public vector<T,N> subgroupClusteredMax(vector<T,N> value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6534,9 +6883,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupClusteredAnd(vector<T,N> value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public vector<T,N> subgroupClusteredAnd(vector<T,N> value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6550,9 +6901,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupClusteredOr(vector<T,N> value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public vector<T,N> subgroupClusteredOr(vector<T,N> value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6566,9 +6919,11 @@ __spirv_version(1.3) [require(spirv)]
 }
 
 __generic<T : __BuiltinLogicalType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_clustered) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupClusteredXor(vector<T,N> value, uint clusterSize)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_clustered)
+[ForceInline]
+[require(glsl_spirv, subgroup_clustered)]
+public vector<T,N> subgroupClusteredXor(vector<T,N> value, uint clusterSize)
 {
     shader_subgroup_preamble<T>();
     __target_switch
@@ -6584,36 +6939,44 @@ __spirv_version(1.3) [require(spirv)]
 // GL_KHR_shader_subgroup_quad
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupQuadBroadcast(T value, uint id)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public T subgroupQuadBroadcast(T value, uint id)
 {
     shader_subgroup_preamble<T>();
     return QuadReadLaneAt(value, id);
 }
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupQuadSwapHorizontal(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public T subgroupQuadSwapHorizontal(T value)
 {
     shader_subgroup_preamble<T>();
     return QuadReadAcrossX(value);
 }
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupQuadSwapVertical(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public T subgroupQuadSwapVertical(T value)
 {
     shader_subgroup_preamble<T>();
     return QuadReadAcrossY(value);
 }
 
 __generic<T : __BuiltinType>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public T subgroupQuadSwapDiagonal(T value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public T subgroupQuadSwapDiagonal(T value)
 {
     shader_subgroup_preamble<T>();
     return QuadReadAcrossDiagonal(value);
@@ -6621,36 +6984,44 @@ __spirv_version(1.3) [require(spirv)]
 
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupQuadBroadcast(vector<T,N> value, uint id)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public vector<T,N> subgroupQuadBroadcast(vector<T,N> value, uint id)
 {
     shader_subgroup_preamble<T>();
     return QuadReadLaneAt(value, id);
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupQuadSwapHorizontal(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public vector<T,N> subgroupQuadSwapHorizontal(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return QuadReadAcrossX(value);
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupQuadSwapVertical(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public vector<T,N> subgroupQuadSwapVertical(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return QuadReadAcrossY(value);
 }
 
 __generic<T : __BuiltinType, let N : int>
-__glsl_extension(GL_KHR_shader_subgroup_quad) [require(glsl)] 
-__spirv_version(1.3) [require(spirv)]
-[ForceInline] public vector<T,N> subgroupQuadSwapDiagonal(vector<T,N> value)
+__spirv_version(1.3)
+__glsl_extension(GL_KHR_shader_subgroup_quad)
+[ForceInline]
+[require(glsl_hlsl_spirv, subgroup_quad)]
+public vector<T,N> subgroupQuadSwapDiagonal(vector<T,N> value)
 {
     shader_subgroup_preamble<T>();
     return QuadReadAcrossDiagonal(value);
@@ -6671,7 +7042,9 @@ public struct atomic_uint
 // types and operations to enable the according ext needed for these operations
 
 __generic<T : __BuiltinType>
-[ForceInline] void typeRequireChecks_atomic_using_float0_tier() 
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+void typeRequireChecks_atomic_using_float0_tier() 
 {
     __target_switch
     {
@@ -6685,7 +7058,9 @@ __generic<T : __BuiltinType>
     }
 }
 __generic<T : __BuiltinType>
-[ForceInline] void typeRequireChecks_atomic_using_float1_tier() 
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+void typeRequireChecks_atomic_using_float1_tier() 
 {
     __target_switch
     {
@@ -6708,7 +7083,9 @@ __generic<T : __BuiltinType>
     }
 }
 __generic<T : __BuiltinType>
-[ForceInline] void typeRequireChecks_atomic_using_float2_tier() 
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+void typeRequireChecks_atomic_using_float2_tier() 
 {
     __target_switch
     {
@@ -6732,6 +7109,7 @@ __generic<T : __BuiltinType>
 }
 
 __generic<T : __BuiltinType>
+[require(glsl_spirv, atomic_glsl)]
 void typeRequireChecks_atomic_using_add()
 {
     __target_switch
@@ -6777,6 +7155,7 @@ void typeRequireChecks_atomic_using_add()
     }
 }
 __generic<T : __BuiltinType>
+[require(glsl_spirv, atomic_glsl)]
 void typeRequireChecks_atomic_using_MinMax()
 {
     __target_switch
@@ -6822,7 +7201,9 @@ void typeRequireChecks_atomic_using_MinMax()
     }
 }
 __generic<T : __BuiltinType>
-[ForceInline] void typeRequireChecks_atomic_using_Logical_CAS() 
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+void typeRequireChecks_atomic_using_Logical_CAS() 
 {
     __target_switch
     {
@@ -6877,9 +7258,11 @@ for (const auto& item : atomics)
 {
 }}}}
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicAdd(inout $(item.name) mem, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicAdd(inout $(item.name) mem, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float1_tier<$(item.name)>();
     typeRequireChecks_atomic_using_add<$(item.name)>();
@@ -6894,9 +7277,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicMin(inout $(item.name) mem, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicMin(inout $(item.name) mem, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float2_tier<$(item.name)>();
     typeRequireChecks_atomic_using_MinMax<$(item.name)>();
@@ -6911,9 +7296,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicMax(inout $(item.name) mem, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicMax(inout $(item.name) mem, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float2_tier<$(item.name)>();
     typeRequireChecks_atomic_using_MinMax<$(item.name)>();
@@ -6928,9 +7315,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicExchange(inout $(item.name) mem, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicExchange(inout $(item.name) mem, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float1_tier<$(item.name)>();
     __target_switch
@@ -6949,9 +7338,11 @@ if(item.isFloat)
     continue;
 }}}}
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicAnd(inout $(item.name) mem, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicAnd(inout $(item.name) mem, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float0_tier<$(item.name)>();
     typeRequireChecks_atomic_using_Logical_CAS<$(item.name)>();
@@ -6969,9 +7360,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicOr(inout $(item.name) mem, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicOr(inout $(item.name) mem, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float0_tier<$(item.name)>();
     typeRequireChecks_atomic_using_Logical_CAS<$(item.name)>();
@@ -6986,9 +7379,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicXor(inout $(item.name) mem, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicXor(inout $(item.name) mem, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float0_tier<$(item.name)>();
     typeRequireChecks_atomic_using_Logical_CAS<$(item.name)>();
@@ -7003,9 +7398,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public $(item.name) atomicCompSwap(inout $(item.name) mem, $(item.name) compare, $(item.name) data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public $(item.name) atomicCompSwap(inout $(item.name) mem, $(item.name) compare, $(item.name) data)
 {
     typeRequireChecks_atomic_using_float0_tier<$(item.name)>();
     typeRequireChecks_atomic_using_Logical_CAS<$(item.name)>();
@@ -7027,9 +7424,11 @@ ${{{{
 // all atomic_uint functions are mangled at compile time, 
 // all types are converted into a field address of a 'uint'
 // relative to the layout(offset) of the atomic_uint 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterIncrement(atomic_uint c)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterIncrement(atomic_uint c)
 {
 
     __target_switch
@@ -7045,7 +7444,8 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__glsl_version(430) [require(glsl)]
+__glsl_version(430) 
+[require(glsl, atomic_glsl)]
 [ForceInline] public uint atomicCounterDecrement_GLSL_helper(atomic_uint c)
 {
     __target_switch
@@ -7057,9 +7457,10 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounter(atomic_uint c)
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounter(atomic_uint c)
 {
     __target_switch
     {
@@ -7077,9 +7478,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterDecrement(atomic_uint c)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterDecrement(atomic_uint c)
 {
     __target_switch
     {
@@ -7101,9 +7504,11 @@ __glsl_version(430) [require(glsl)]
     }   
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterAdd(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterAdd(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7118,9 +7523,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterSubtract(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterSubtract(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7138,9 +7545,11 @@ __glsl_version(430) [require(glsl)]
     }   
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterMin(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterMin(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7155,9 +7564,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterMax(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterMax(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7172,9 +7583,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterAnd(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterAnd(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7189,9 +7602,11 @@ __glsl_version(430) [require(glsl)]
     }   
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterOr(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterOr(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7206,9 +7621,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterXor(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterXor(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7223,9 +7640,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterExchange(atomic_uint c, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterExchange(atomic_uint c, uint data)
 {
     __target_switch
     {
@@ -7240,9 +7659,11 @@ __glsl_version(430) [require(glsl)]
     }
 }
 
-__spirv_version(1.0)[require(spirv)]
-__glsl_version(430) [require(glsl)]
-[ForceInline] public uint atomicCounterCompSwap(atomic_uint c, uint compare, uint data)
+
+__glsl_version(430)
+[ForceInline]
+[require(glsl_spirv, atomic_glsl)]
+public uint atomicCounterCompSwap(atomic_uint c, uint compare, uint data)
 {
     __target_switch
     {
@@ -7259,105 +7680,105 @@ __glsl_version(430) [require(glsl)]
 
 /// Section 8.14. Fragment Processing Functions
 
-[require(any_gfx_target, fragmentprocessing)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing)]
 public float dFdx(float p)
 {
     return ddx(p);
 }
-[require(any_gfx_target, fragmentprocessing)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing)]
 public vector<float, N> dFdx(vector<float, N> p)
 {
     return ddx(p);
 }
 
-[require(any_gfx_target, fragmentprocessing)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing)]
 public float dFdy(float p)
 {
     return ddy(p);
 }
-[require(any_gfx_target, fragmentprocessing)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing)]
 public vector<float, N> dFdy(vector<float, N> p)
 {
     return ddy(p);
 }
 
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public float dFdxFine(float p)
 {
     return ddx_fine(p);
 }
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public vector<float, N> dFdxFine(vector<float, N> p)
 {
     return ddx_fine(p);
 }
 
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public float dFdyFine(float p)
 {
     return ddy_fine(p);
 }
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public vector<float, N> dFdyFine(vector<float, N> p)
 {
     return ddy_fine(p);
 }
 
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public float dFdxCoarse(float p)
 {
     return ddx_coarse(p);
 }
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public vector<float, N> dFdxCoarse(vector<float, N> p)
 {
     return ddx_coarse(p);
 }
 
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public float dFdyCoarse(float p)
 {
     return ddy_coarse(p);
 }
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public vector<float, N> dFdyCoarse(vector<float, N> p)
 {
     return ddy_coarse(p);
 }
 
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public float fwidthFine(float p)
 {
     __target_switch
@@ -7377,10 +7798,10 @@ public float fwidthFine(float p)
     }
     }
 }
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public vector<float, N> fwidthFine(vector<float, N> p)
 {
     __target_switch
@@ -7401,9 +7822,9 @@ public vector<float, N> fwidthFine(vector<float, N> p)
     }
 }
 
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public float fwidthCoarse(float p)
 {
     __target_switch
@@ -7423,10 +7844,10 @@ public float fwidthCoarse(float p)
     }
     }
 }
-[require(any_gfx_target, fragmentprocessing_derivativecontrol)]
 __generic<let N : int>
 [__NoSideEffect]
 [ForceInline]
+[require(glsl_hlsl_spirv, fragmentprocessing_derivativecontrol)]
 public vector<float, N> fwidthCoarse(vector<float, N> p)
 {
     __target_switch
@@ -7447,17 +7868,13 @@ public vector<float, N> fwidthCoarse(vector<float, N> p)
     }
 }
 
-[require(any_gfx_target, fragmentprocessing)]
 [__NoSideEffect]
 [__GLSLRequireShaderInputParameter(0)]
+[require(glsl_spirv, fragmentprocessing)]
 public float interpolateAtCentroid(__ref float interpolant)
 {
     __target_switch
     {
-    case hlsl:
-    {
-        return EvaluateAttributeAtCentroid(interpolant);
-    }
     case glsl: __intrinsic_asm "interpolateAtCentroid($0)";
     case spirv:
     {
@@ -7469,18 +7886,14 @@ public float interpolateAtCentroid(__ref float interpolant)
     }
     }
 }
-[require(any_gfx_target, fragmentprocessing)]
 __generic<let N : int>
 [__NoSideEffect]
 [__GLSLRequireShaderInputParameter(0)]
+[require(glsl_spirv, fragmentprocessing)]
 public vector<float, N> interpolateAtCentroid(__ref vector<float, N> interpolant)
 {
     __target_switch
     {
-    case hlsl:
-    {
-        return EvaluateAttributeAtCentroid(interpolant);
-    }
     case glsl: __intrinsic_asm "interpolateAtCentroid($0)";
     case spirv:
     {
@@ -7493,17 +7906,13 @@ public vector<float, N> interpolateAtCentroid(__ref vector<float, N> interpolant
     }
 }
 
-[require(any_gfx_target, fragmentprocessing)]
 [__NoSideEffect]
 [__GLSLRequireShaderInputParameter(0)]
+[require(glsl_spirv, fragmentprocessing)]
 public float interpolateAtSample(__ref float interpolant, int sample)
 {
     __target_switch
     {
-    case hlsl:
-    {
-        return EvaluateAttributeAtSample(interpolant, sample);
-    }
     case glsl: __intrinsic_asm "interpolateAtSample($0,$1)";
     case spirv:
     {
@@ -7515,18 +7924,14 @@ public float interpolateAtSample(__ref float interpolant, int sample)
     }
     }
 }
-[require(any_gfx_target, fragmentprocessing)]
 __generic<let N : int>
 [__NoSideEffect]
 [__GLSLRequireShaderInputParameter(0)]
+[require(glsl_spirv, fragmentprocessing)]
 public vector<float, N> interpolateAtSample(__ref vector<float, N> interpolant, int sample)
 {
     __target_switch
     {
-    case hlsl:
-    {
-        return EvaluateAttributeAtSample(interpolant, sample);
-    }
     case glsl: __intrinsic_asm "interpolateAtSample($0,$1)";
     case spirv:
     {
@@ -7539,9 +7944,9 @@ public vector<float, N> interpolateAtSample(__ref vector<float, N> interpolant,
     }
 }
 
-[require(glsl_spirv, fragmentprocessing)]
 [__NoSideEffect]
 [__GLSLRequireShaderInputParameter(0)]
+[require(glsl_spirv, fragmentprocessing)]
 public float interpolateAtOffset(__ref float interpolant, vec2 offset)
 {
     __target_switch
@@ -7557,10 +7962,10 @@ public float interpolateAtOffset(__ref float interpolant, vec2 offset)
     }
     }
 }
-[require(glsl_spirv, fragmentprocessing)]
 __generic<let N : int>
 [__NoSideEffect]
 [__GLSLRequireShaderInputParameter(0)]
+[require(glsl_spirv, fragmentprocessing)]
 public vector<float, N> interpolateAtOffset(__ref vector<float, N> interpolant, vec2 offset)
 {
     __target_switch
@@ -7650,8 +8055,8 @@ public vec4 noise4(vector<float, N> x)
 // control flow.
 // TODO: if called after a return, error.
 
-[require(any_gfx_target, compute_tess_gfx)]
 [ForceInline]
+[require(glsl_hlsl_spirv, shader_stages_compute_tesscontrol_tesseval)]
 public void barrier()
 {
     __target_switch
@@ -7673,8 +8078,8 @@ public void barrier()
 
 /// Section 8.17. Shader Memory Control Functions
 
-[require(shadermemorycontrol)]
 [ForceInline]
+[require(glsl_hlsl_spirv, shadermemorycontrol)]
 public void memoryBarrier()
 {
     __target_switch
@@ -7699,8 +8104,8 @@ public void memoryBarrier()
 // glslang will compile with `AtomicCounterMemory` since it does not use
 // the `AtomicStorage` OpCapability which is required for `AtomicCounterMemory`.
 // this is invalid/undefined spir-v for vulkan targets and should not be followed
-[require(any_gfx_target, shadermemorycontrol_compute)]
 [ForceInline]
+[require(glsl_hlsl_spirv, shadermemorycontrol_compute)]
 public void memoryBarrierAtomicCounter()
 {
     __target_switch
@@ -7717,8 +8122,8 @@ public void memoryBarrierAtomicCounter()
     }
     }
 }
-[require(shadermemorycontrol)]
 [ForceInline]
+[require(glsl_hlsl_spirv, shadermemorycontrol)]
 public void memoryBarrierBuffer()
 {
     __target_switch
@@ -7736,8 +8141,8 @@ public void memoryBarrierBuffer()
     }
 }
 
-[require(any_gfx_target, shadermemorycontrol_compute)]
 [ForceInline]
+[require(glsl_hlsl_spirv, shadermemorycontrol_compute)]
 public void memoryBarrierShared()
 {
     __target_switch
@@ -7754,8 +8159,8 @@ public void memoryBarrierShared()
     }
     }
 }
-[require(shadermemorycontrol)]
 [ForceInline]
+[require(glsl_hlsl_spirv, shadermemorycontrol)]
 public void memoryBarrierImage()
 {
     __target_switch
@@ -7771,8 +8176,8 @@ public void memoryBarrierImage()
     }
     }
 }
-[require(any_gfx_target, shadermemorycontrol_compute)]
 [ForceInline]
+[require(glsl_hlsl_spirv, shadermemorycontrol_compute)]
 public void groupMemoryBarrier()
 {
     __target_switch
@@ -7822,9 +8227,9 @@ ${{{{
 }}}}
 
     __generic<T>
-    [require(glsl_spirv, subpass)]
     [__NoSideEffect]
     [ForceInline]
+    [require(glsl_hlsl_spirv, subpass)]
     public T subpassLoad(__SubpassImpl<T,0> subpass)
     {
         __target_switch
@@ -7843,9 +8248,9 @@ ${{{{
         }
     }
     __generic<T>
-    [require(glsl_spirv, subpass)]
     [__NoSideEffect]
     [ForceInline]
+    [require(glsl_hlsl_spirv, subpass)]
     public T subpassLoad(__SubpassImpl<T,1> subpass, int sample)
     {
         __target_switch
@@ -7871,27 +8276,27 @@ ${{{{
 // alternatives
 __glsl_version(460)
 __spirv_version(1.3)
-[require(shaderinvocationgroup)]
 [NonUniformReturn]
 [ForceInline]
+[require(glsl_hlsl_spirv, shaderinvocationgroup)]
 public bool anyInvocation(bool value)
 {
     return WaveActiveAnyTrue(value);
 }
 __glsl_version(460)
 __spirv_version(1.3)
-[require(shaderinvocationgroup)]
 [NonUniformReturn]
 [ForceInline]
+[require(glsl_hlsl_spirv, shaderinvocationgroup)]
 public bool allInvocations(bool value)
 {
     return WaveActiveAllTrue(value);
 }
 __glsl_version(460)
 __spirv_version(1.3)
-[require(shaderinvocationgroup)]
 [NonUniformReturn]
 [ForceInline]
+[require(glsl_hlsl_spirv, shaderinvocationgroup)]
 public bool allInvocationsEqual(bool value)
 {
     return WaveActiveAllEqual(value);