From a10d9cd8767e88a064719d71cc97144ba8b112d1 Mon Sep 17 00:00:00 2001
From: jsmall-nvidia <jsmall@nvidia.com>
Date: Tue, 10 Mar 2020 12:31:25 -0400
Subject: WIP Prefix Sum for CUDA (#1268)

* Fix some typos.

* Add wave-prefix-sum.slang test

* First pass at implementing prefixSum.

* Small improvments to prefixSum CUDA.

* Small improvement to prefix sum.

* Enable prefix sum in stdlib.
---
 source/slang/hlsl.meta.slang | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

(limited to 'source')

diff --git a/source/slang/hlsl.meta.slang b/source/slang/hlsl.meta.slang
index 4b717d540..b43cd009f 100644
--- a/source/slang/hlsl.meta.slang
+++ b/source/slang/hlsl.meta.slang
@@ -2497,12 +2497,12 @@ bool WaveIsFirstLane();
 __generic<T : __BuiltinArithmeticType>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveMul($0)")
+__target_intrinsic(glsl, "subgroupExclusiveMul($0)")
 T WavePrefixProduct(T expr);
 __generic<T : __BuiltinArithmeticType, let N : int>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveMul($0)")
+__target_intrinsic(glsl, "subgroupExclusiveMul($0)")
 vector<T,N> WavePrefixProduct(vector<T,N> expr);
 __generic<T : __BuiltinArithmeticType, let N : int, let M : int>
 matrix<T,N,M> WavePrefixProduct(matrix<T,N,M> expr);
@@ -2510,12 +2510,13 @@ matrix<T,N,M> WavePrefixProduct(matrix<T,N,M> expr);
 __generic<T : __BuiltinArithmeticType>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveAdd($0)")
+__target_intrinsic(glsl, "subgroupExclusiveAdd($0)")
+__target_intrinsic(cuda, "_wavePrefixSum($0)")
 T WavePrefixSum(T expr);
 __generic<T : __BuiltinArithmeticType, let N : int>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveAdd($0)")
+__target_intrinsic(glsl, "subgroupExclusiveAdd($0)")
 vector<T,N> WavePrefixSum(vector<T,N> expr);
 __generic<T : __BuiltinArithmeticType, let N : int, let M : int>
 matrix<T,N,M> WavePrefixSum(matrix<T,N,M> expr);
@@ -2523,11 +2524,11 @@ matrix<T,N,M> WavePrefixSum(matrix<T,N,M> expr);
 __generic<T : __BuiltinArithmeticType>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveAnd($0)")
+__target_intrinsic(glsl, "subgroupExclusiveAnd($0)")
 T WaveMultiPrefixBitAnd(T expr);
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveAnd($0)")
+__target_intrinsic(glsl, "subgroupExclusiveAnd($0)")
 __generic<T : __BuiltinArithmeticType, let N : int>
 vector<T,N> WaveMultiPrefixBitAnd(vector<T,N> expr);
 __generic<T : __BuiltinArithmeticType, let N : int, let M : int>
@@ -2536,12 +2537,12 @@ matrix<T,N,M> WaveMultiPrefixBitAnd(matrix<T,N,M> expr);
 __generic<T : __BuiltinArithmeticType>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveOr($0)")
+__target_intrinsic(glsl, "subgroupExclusiveOr($0)")
 T WaveMultiPrefixBitOr(T expr);
 __generic<T : __BuiltinArithmeticType, let N : int>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveOr($0)")
+__target_intrinsic(glsl, "subgroupExclusiveOr($0)")
 vector<T,N> WaveMultiPrefixBitOr(vector<T,N> expr);
 __generic<T : __BuiltinArithmeticType, let N : int, let M : int>
 matrix<T,N,M> WaveMultiPrefixBitOr(matrix<T,N,M> expr);
@@ -2549,12 +2550,12 @@ matrix<T,N,M> WaveMultiPrefixBitOr(matrix<T,N,M> expr);
 __generic<T : __BuiltinArithmeticType>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveXor($0)")
+__target_intrinsic(glsl, "subgroupExclusiveXor($0)")
 T WaveMultiPrefixBitXor(T expr);
 __generic<T : __BuiltinArithmeticType, let N : int>
 __glsl_extension(GL_KHR_shader_subgroup_arithmetic)
 __spirv_version(1.3)
-__target_intrinsic(glsl, "subgroupExcusiveXor($0)")
+__target_intrinsic(glsl, "subgroupExclusiveXor($0)")
 vector<T,N> WaveMultiPrefixBitXor(vector<T,N> expr);
 __generic<T : __BuiltinArithmeticType, let N : int, let M : int>
 matrix<T,N,M> WaveMultiPrefixBitXor(matrix<T,N,M> expr);
-- 
cgit v1.2.3