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.

3 files changed, 38 insertions, 0 deletions

diff --git a/tests/compute/rw-texture-simple.slang b/tests/compute/rw-texture-simple.slang
new file mode 100644
index 000000000..dde0ecd4c
--- /dev/null
+++ b/tests/compute/rw-texture-simple.slang
@@ -0,0 +1,27 @@
+//TEST(compute):COMPARE_COMPUTE_EX:-cpu -compute 
+// Doesn't work on DX11 currently - locks up on binding
+//DISABLE_TEST(compute):COMPARE_COMPUTE_EX:-slang -compute
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 
+//TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile cs_6_0 -use-dxil
+// TODO(JS): Doesn't work on vk currently, because createTextureView not implemented on vk renderer
+//DISABLE_TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute
+//TEST(compute):COMPARE_COMPUTE_EX:-cuda -compute 
+
+//TEST_INPUT: RWTexture1D(format=R_Float32, size=4, content = one):name rwt1D
+RWTexture1D<float> rwt1D;
+
+//TEST_INPUT: ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
+RWStructuredBuffer<float> outputBuffer;
+
+[numthreads(4, 4, 1)]
+void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
+{
+    int idx = dispatchThreadID.x;
+    float u = idx * (1.0f / 4);
+    
+    float val = 0.0f;
+ 
+    val += rwt1D.Load(idx);
+ 
+    outputBuffer[idx] = val;
+}
diff --git a/tests/compute/rw-texture-simple.slang.expected.txt b/tests/compute/rw-texture-simple.slang.expected.txt
new file mode 100644
index 000000000..cc5e55ab6
--- /dev/null
+++ b/tests/compute/rw-texture-simple.slang.expected.txt
@@ -0,0 +1,4 @@
+3F800000
+3F800000
+3F800000
+3F800000
diff --git a/tests/compute/texture-simple.slang b/tests/compute/texture-simple.slang
index 8e72250ff..df990ec7a 100644
--- a/tests/compute/texture-simple.slang
+++ b/tests/compute/texture-simple.slang
@@ -6,6 +6,10 @@
 //DISABLE_TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute
 //TEST(compute):COMPARE_COMPUTE_EX:-cuda -compute 
 
+// Doesn't work on CUDA, not clear why yet
+//DISABLE_TEST_INPUT: Texture1D(format=R_Float32, size=4, content = one, mipMaps=1):name tLoad1D
+//Texture1D<float> tLoad1D;
+
 //TEST_INPUT: Texture1D(size=4, content = one):name t1D
 Texture1D<float> t1D;
 //TEST_INPUT: Texture2D(size=4, content = one):name t2D
@@ -35,6 +39,7 @@ void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
     float u = idx * (1.0f / 4);
     
     float val = 0.0f;
+   
     val += t1D.SampleLevel(samplerState, u, 0);
     val += t2D.SampleLevel(samplerState, float2(u, u), 0);
     val += t3D.SampleLevel(samplerState, float3(u, u, u), 0);
@@ -44,5 +49,7 @@ void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
     val += t2DArray.SampleLevel(samplerState, float3(u, u, 0), 0);
     val += tCubeArray.SampleLevel(samplerState, float4(u, u, u, 0), 0);
  
+    //val += tLoad1D.Load(int2(idx, 0));
+ 
     outputBuffer[idx] = val;
 }