CUDA support improvements (#1168)

* Add test result for compile-to-cuda

* Add RAII for some CUDA types to simplify usage.

* First pass handling of some instrinsics on CUDA (for example transcendentals)

* CUDA working with built in intrinsics.

* Add missing CUDA prelude intrinsics.

* CUDA matches CPU output on simple-cross-compile.slang

* First pass at hlsl-scalar-float-intrinsic.slang test.

* Fix smoothstep impl on CUDA and CPU.

* Fixed step intrinsic on CUDA/CPU.

* Added operator[] to Matrix for C++, to allow row access.
Needs a fix for CUDA.

* Fixed warning on clang build.

2 files changed, 113 insertions, 0 deletions

diff --git a/tests/cross-compile/simple-cross-compile.slang b/tests/cross-compile/simple-cross-compile.slang
new file mode 100644
index 000000000..e5fe9d3cc
--- /dev/null
+++ b/tests/cross-compile/simple-cross-compile.slang
@@ -0,0 +1,109 @@
+//TEST(compute):COMPARE_COMPUTE:-cpu
+//TEST(compute):COMPARE_COMPUTE:-cuda
+
+enum Color
+{
+    Red,
+    Green = 2,
+    Blue,
+}
+
+int test(int val)
+{
+    Color c = Color.Red;
+
+    if(val > 1)
+    {
+        c = Color.Green;
+    }
+
+    if(c == Color.Red)
+    {
+        if(val & 1)
+        {
+            c = Color.Blue;
+        }
+    }
+
+    switch(c)
+    {
+    case Color.Red:
+        val = 1;
+        break;
+
+    case Color.Green:
+        val = 2;
+        break;
+
+    case Color.Blue:
+        val = 3;
+        break;
+
+    default:
+        val = -1;
+        break;
+    }
+
+    return (val << 4) + int(c);
+}
+
+float sum(float a[3])
+{
+    float total = a[0];
+    for (int i = 1; i < 3; ++i)
+    {
+        total += a[i];
+    }
+    return total;
+}
+
+struct Thing
+{
+    int a;
+    float b;
+};
+
+//TEST_INPUT:ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
+RWStructuredBuffer<int> outputBuffer;
+
+[numthreads(4, 1, 1)]
+void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
+{
+    uint tid = dispatchThreadID.x;
+
+    Thing thing = { 10, -1.0 };
+
+    float array[3] = { thing.a, 2, 3};
+
+    float anotherArray[] = { 1, 2, 5 };
+
+    array[0] += anotherArray[1];
+
+    matrix<float, 2, 3> mat = { { sum(array), 1, 2 }, { 3, 4, 5} };
+    vector<float, 2> vec = { float(tid + 1), float(tid + 2) };
+
+    vec += float2(7, 11);
+
+    vector<float, 3> vec2 = max(sin(mul(vec, mat)), float3(1, 2, -1));
+    vector<float, 3> vec3 = mul(vec, mat);
+    
+    float3 vec4 = lerp(vec2, vec3, float3(tid * (1.0f / 4), 1, 1));
+    
+    float3 crossVec = normalize(cross(vec4, vec4) + float3(2, 3, 1));
+    
+    vec2.x = fmod(crossVec.y, crossVec.x);
+    
+    vec2 = fmod(vec2, crossVec);
+    
+    vec2 += (-vec2.zyx) * 2 + crossVec * length(crossVec) + reflect(vec4, normalize(crossVec));
+    
+    vector<bool, 3> z = vec2 > 0;
+
+    int val = (int(tid) + (any(z) ? 1 : 0) + (all(z) ? 2 : 0)) % 100;
+    
+    val = asint(asfloat(asuint(asfloat(val))));
+    
+    val = test(val);
+
+    outputBuffer[tid] = val + int(dot(vec2, vec4));
+}
\ No newline at end of file
diff --git a/tests/cross-compile/simple-cross-compile.slang.expected.txt b/tests/cross-compile/simple-cross-compile.slang.expected.txt
new file mode 100644
index 000000000..c99b80180
--- /dev/null
+++ b/tests/cross-compile/simple-cross-compile.slang.expected.txt
@@ -0,0 +1,4 @@
+147
+FFFFE732
+FFFFCCE6
+FFFFB6C7