Preliminary CUDA half maths (#1827)

* #include an absolute path didn't work - because paths were taken to always be relative.

* Split out StringEscapeUtil.

* Added StringEscapeUtil.

* Fix typo in unix quoting type.

* Small comment improvements.

* Try to fix linux linking issue.

* Fix typo.

* Attempt to fix linux link issue.

* Update VS proj even though nothing really changed.

* Fix another typo issue.

* Fix for windows issue.
Fixed bug.

* Make separate Utils for escaping.

* Fix typo.

* Split out into StringEscapeHandler.

* Windows shell does handle removing quotes (so remove code to remove them).

* Handle unescaping if not initiating using the shell.

* Slight improvement around shell like decoding.

* Simplify command extraction.

* Add shared-library category type.

* Fix bug in command extraction.

* Typo in transcendental category.

* Enable unit-test on in smoke test category.

* Make parsing failing output as a failing test.

* Fixes for transcendental tests. Disable tests that do not work.

* Changed category parsing.

* Removed the TestResult parameter from _gatherTestsForFile.
Made testsList only output.

* Remove testing if all tests were disabled.

* Make args of CommandLine always unescaped.

* Add category.

* Don't need escaping on unix/linux.

* Remove some no longer used functions.

* Add requireSMVersion to CUDAExtensionTracker.

* half-calc.slang now works for CUDA.

* bit-cast-16-bit works on CUDA.

* WIP handling of CUDA vector<half> types.

* Half swizzle CUDA.

* Half vector test.

* Fix swizzle half bug.

* Fix compilation issue with narrowing to Index.

Co-authored-by: Tim Foley <tfoleyNV@users.noreply.github.com>

4 files changed, 42 insertions, 1 deletions

diff --git a/tests/compute/half-calc.slang b/tests/compute/half-calc.slang
index 57efebe53..e0dd01315 100644
--- a/tests/compute/half-calc.slang
+++ b/tests/compute/half-calc.slang
@@ -1,6 +1,6 @@
 //DISABLE_TEST(compute):COMPARE_COMPUTE:-dx12 -compute -use-dxil -profile cs_6_2 -render-features half -shaderobj
 //TEST(compute):COMPARE_COMPUTE:-vk -compute -profile cs_6_2 -render-features half -shaderobj
-
+//TEST(compute):COMPARE_COMPUTE:-cuda -compute -render-features half -shaderobj
 
 // Test for doing a calculation using half
 
diff --git a/tests/compute/half-vector-calc.slang b/tests/compute/half-vector-calc.slang
new file mode 100644
index 000000000..5594c38fd
--- /dev/null
+++ b/tests/compute/half-vector-calc.slang
@@ -0,0 +1,35 @@
+//DISABLE_TEST(compute):COMPARE_COMPUTE:-dx12 -compute -output-using-type -use-dxil -profile cs_6_2 -render-features half -shaderobj
+//TEST(compute):COMPARE_COMPUTE:-vk -compute -output-using-type -profile cs_6_2 -render-features half -shaderobj
+//TEST(compute):COMPARE_COMPUTE:-cuda -compute -output-using-type -render-features half -shaderobj
+
+// Test for doing a calculation using half
+
+//TEST_INPUT:ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
+RWStructuredBuffer<float> outputBuffer;
+
+[numthreads(4, 1, 1)]
+void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
+{
+    uint tid = dispatchThreadID.x;
+    int x = tid.x;
+    
+    half2 v3 = half2(float(x));
+    
+    half2 v0 = half2(x * 2.0f, x * 0.5f);
+    half3 v1 = half3(x * 2.0f, x * 0.5f, x - 1.0f);
+    half4 v2 = half4(x + 1, x - 1, x + 2 , x - 2);
+    
+    v1 += v0.yxy;
+    v1 += v2.wzy;
+    v2 += v0.xyxy;
+    
+    v0 = v0 + v0 * v0;
+    v1 = v1 + v1 * v1;
+    v2 = v2 + v2 * v2;
+    
+    half o2 = v2.x + v2.y + v2.z + v2.w;
+    half o1 = v1.x + v1.y + v1.z;
+    half o0 = v0.x + v0.y;
+        
+    outputBuffer[tid] = o0 + o1 + o2 + v3.y;
+}
diff --git a/tests/compute/half-vector-calc.slang.expected.txt b/tests/compute/half-vector-calc.slang.expected.txt
new file mode 100644
index 000000000..64beb1dd1
--- /dev/null
+++ b/tests/compute/half-vector-calc.slang.expected.txt
@@ -0,0 +1,5 @@
+type: float
+20.000000
+98.500000
+292.000000
+600.500000
diff --git a/tests/hlsl-intrinsic/bit-cast/bit-cast-16-bit.slang b/tests/hlsl-intrinsic/bit-cast/bit-cast-16-bit.slang
index 0241ff9cd..28f8973f6 100644
--- a/tests/hlsl-intrinsic/bit-cast/bit-cast-16-bit.slang
+++ b/tests/hlsl-intrinsic/bit-cast/bit-cast-16-bit.slang
@@ -2,6 +2,7 @@
 
 //TEST(compute):COMPARE_COMPUTE_EX:-slang -compute -dx12 -use-dxil -profile sm_6_2 -shaderobj
 //TEST(compute, vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
+//TEST(compute):COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
 
 //TEST_INPUT:ubuffer(data=[0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16], stride=4):name inputBuffer
 RWStructuredBuffer<int> inputBuffer;