From 1f401d04e32c6feaeb35243ea5bfc2b14520344b Mon Sep 17 00:00:00 2001
From: jsmall-nvidia <jsmall@nvidia.com>
Date: Thu, 20 Feb 2020 18:24:00 -0500
Subject: WIP on RWTexture types on CUDA/CPU (#1234)

* CUDA support for array of resources.

* * Add support for Texture2DArray on CPU
* Expand texture-simple.slang to test Texture2DArray

* Reorganise CUDAComputeUtil to split out createTextureResource.

* Add TextureCubeArray support for CPU/CUDA targets.

* Pulled out CUDAResource
Renamed derived classes to reflect that change.

* Creation of SurfObject type.

* Functions to return read/write access for simplifying future additions.

* WIP for RWTexture access on CPU/CUDA.

* CUsurfObject cannot have mips.

* Ability to set number of mips on test data.
Preliminary support for CUsurfObj and RWTexture1D on CUDA.
CUDA docs improvements.

* Fix typo.
---
 prelude/slang-cpp-types.h    | 15 +++++++++++++++
 prelude/slang-cuda-prelude.h | 10 ++++++++++
 2 files changed, 25 insertions(+)

(limited to 'prelude')

diff --git a/prelude/slang-cpp-types.h b/prelude/slang-cpp-types.h
index f62333f68..563b4b6e9 100644
--- a/prelude/slang-cpp-types.h
+++ b/prelude/slang-cpp-types.h
@@ -343,6 +343,21 @@ struct TextureCubeArray
     ITextureCubeArray* texture;              
 };
 
+/* !!!!!!!!!!!!!!!!!!!!!!!!!!! RWTexture !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! */
+
+struct IRWTexture1D
+{
+    virtual void Load(int32_t loc, void* out) = 0;
+};
+
+template <typename T>
+struct RWTexture1D
+{
+    T Load(int32_t loc) const { T out; texture->Load(loc, &out); return out; }
+    
+    IRWTexture1D* texture;              
+};
+
 /* Varying input for Compute */
 
 /* Used when running a single thread */
diff --git a/prelude/slang-cuda-prelude.h b/prelude/slang-cuda-prelude.h
index b81acba1e..1938e3dc1 100644
--- a/prelude/slang-cuda-prelude.h
+++ b/prelude/slang-cuda-prelude.h
@@ -38,6 +38,16 @@
 // Here we don't have the index zeroing behavior, as such bounds checks are generally not on GPU targets either. 
 #ifndef SLANG_CUDA_FIXED_ARRAY_BOUND_CHECK
 #   define SLANG_CUDA_FIXED_ARRAY_BOUND_CHECK(index, count) SLANG_PRELUDE_ASSERT(index < count); 
+#endif
+
+ // This macro handles how out-of-range surface coordinates are handled; 
+ // I can equal
+ // cudaBoundaryModeClamp, in which case out-of-range coordinates are clamped to the valid range
+ // cudaBoundaryModeZero, in which case out-of-range reads return zero and out-of-range writes are ignored
+ // cudaBoundaryModeTrap, in which case out-of-range accesses cause the kernel execution to fail. 
+ 
+#ifndef SLANG_CUDA_BOUNDARY_MODE
+#   define SLANG_CUDA_BOUNDARY_MODE cudaBoundaryModeZero
 #endif
 
 template <typename T, size_t SIZE>
-- 
cgit v1.2.3