CUDA: Fix compiler crash with unsized array field - nonuniformres-as-… (#8380)

…function-parameter.slang #8315

Root Cause:
CUDA compilation crashed with `assert failure:
!seenFinalUnsizedArrayField` because unsized arrays like
`RWStructuredBuffer<uint> globalBuffer[]` were not the final field in
generated parameter structs, violating the layout constraint in
slang-ir-layout.cpp.

Fix:
Extended `collectGlobalUniformParameters` to automatically reorder
struct fields for CUDA targets - regular fields first, unsized arrays
last. Other targets preserve original order.

Impact:
- Enables CUDA support for nonuniform resource indexing as function
parameters
- Zero impact on existing GLSL/HLSL/SPIRV targets
- Automatic handling - no manual parameter reordering required

Files: slang-emit.cpp, slang-ir-collect-global-uniforms.cpp/.h, test
file

---------

Co-authored-by: slangbot <ellieh+slangbot@nvidia.com>
Co-authored-by: slangbot <186143334+slangbot@users.noreply.github.com>
Co-authored-by: Ellie Hermaszewska <ellieh@nvidia.com>

1 files changed, 5 insertions, 0 deletions

diff --git a/tests/compute/nonuniformres-as-function-parameter.slang b/tests/compute/nonuniformres-as-function-parameter.slang
index 38fb2a478..fcf8598f6 100644
--- a/tests/compute/nonuniformres-as-function-parameter.slang
+++ b/tests/compute/nonuniformres-as-function-parameter.slang
@@ -2,6 +2,7 @@
 //TEST:SIMPLE(filecheck=CHECK_GLSL_SPV):-target spirv -entry main -stage compute -emit-spirv-via-glsl
 //TEST:SIMPLE(filecheck=CHECK_GLSL):-target glsl -entry main -stage compute
 //TEST:SIMPLE(filecheck=CHECK_HLSL):-target hlsl -entry main -stage compute
+//TEST:SIMPLE(filecheck=CHECK_CUDA):-target cuda -entry main -stage compute
 RWStructuredBuffer<uint> globalBuffer[] : register(u0, space1);
 RWStructuredBuffer<uint3> outputBuffer;
 
@@ -81,6 +82,7 @@ void main(uint2 pixelIndex : SV_DispatchThreadID)
 
     // CHECK_GLSL: func_0({{.*}}nonuniformEXT({{.*}}))
     // CHECK_HLSL: func_0(globalBuffer_0[NonUniformResourceIndex({{.*}})])
+    // CHECK_CUDA: func_{{[0-9]+}}(globalParams_{{[0-9]+}}->globalBuffer_{{[0-9]+}}[{{.*}}])
     MyStruct myStruct = func(buffer);
 
     int bufferIdx2 = pixelIndex.y;
@@ -103,6 +105,7 @@ void main(uint2 pixelIndex : SV_DispatchThreadID)
 
     // CHECK_GLSL: func_1({{.*}}nonuniformEXT({{.*}}))
     // CHECK_HLSL: func_0(globalBuffer_0[NonUniformResourceIndex({{.*}})])
+    // CHECK_CUDA: func_{{[0-9]+}}(globalParams_{{[0-9]+}}->globalBuffer_{{[0-9]+}}[{{.*}}])
     MyStruct myStruct2 = func(buffer2);
 
     // Test case 3: Test the case that we handle the uniformity correctly, the NonUniformResourceIndex will not propagate
@@ -114,6 +117,7 @@ void main(uint2 pixelIndex : SV_DispatchThreadID)
 
     // Test to make sure this command is not decorated with NonUniform:
     // CHECK_SPV-NOT: OpDecorate %[[VAR4]] NonUniform
+    // CHECK_CUDA: func_{{[0-9]+}}(globalParams_{{[0-9]+}}->globalBuffer_{{[0-9]+}}[{{.*}}])
     MyStruct myStruct3 = func(buffer3);
 
 
@@ -130,6 +134,7 @@ void main(uint2 pixelIndex : SV_DispatchThreadID)
     //
     // Since after the nested cast, the index data type is 'uint' now, make sure it calls the same function as the test case 1.
     // CHECK_GLSL: func_0({{.*}}nonuniformEXT({{.*}}))
+    // CHECK_CUDA: func_{{[0-9]+}}(globalParams_{{[0-9]+}}->globalBuffer_{{[0-9]+}}[{{.*}}])
     RWStructuredBuffer<uint> buffer4 = globalBuffer[(uint)((int)NonUniformResourceIndex(bufferIdx))];
     MyStruct myStruct4 = func(buffer4);