Add Mesh and Task shader support to GFX (#3190)

* Bump vulkan headers

Also just use vulkan-headers as a submodule

* Add drawMeshTasks to gfx graphics pipelines

* Add DispatchMesh overload with no payload, with GLSL intrinsic

* Require spirv 1.4 for mesh shaders

* Add vulkan mesh shader feature discovery

* Add mesh shader stage bits to vk-util

* Add mesh and task shader support to render-test

* Add mesh and task tests

* Preserve "payload" specifier in task shaders

* Add mesh shader pipeline support to gfx

* Add TODO

* Add numThreads attribute for amplification stage

* Add payload to task shader test

* Drop dependency on d3dx12

* Allow passing payloads from task to mesh shaders

* regenerate vs projects

* check DispatchMesh name correctly

* Add mesh shader tests to failing tests

* Detect wave-ops feature on vulkan

* Add fuse-product to expected failures

This fails because the global varaible `count` is not initialized

* Add required extension to WaveMaskMatch SPIR-V impl

* Remove meshShader member from pipeline desc

* Identify mesh shader support on d3d12

3 files changed, 301 insertions, 0 deletions

diff --git a/tests/pipeline/rasterization/mesh/simple.slang b/tests/pipeline/rasterization/mesh/simple.slang
new file mode 100644
index 000000000..00047aaad
--- /dev/null
+++ b/tests/pipeline/rasterization/mesh/simple.slang
@@ -0,0 +1,86 @@
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHECK): -mesh -output-using-type -dx12 -use-dxil -profile sm_6_6 -render-features mesh-shader
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHECK): -mesh -output-using-type -vk -profile glsl_450+spirv_1_4 -render-features mesh-shader
+
+// To test a simple mesh shader, we'll generate 4 triangles, the vertices of
+// each one will hold the triangle index and a value (the square). The fragment
+// shader will write the value to the specified index of the output buffer.
+
+// CHECK:      0
+// CHECK-NEXT: 1
+// CHECK-NEXT: 4
+// CHECK-NEXT: 9
+
+//TEST_INPUT: ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
+
+RWStructuredBuffer<float> outputBuffer;
+
+cbuffer Uniforms
+{
+	float4x4 modelViewProjection;
+}
+
+//
+// Mesh shader
+//
+
+const static float2 positions[3] = {
+  float2(0.0, -0.5),
+  float2(0.5, 0.5),
+  float2(-0.5, 0.5)
+};
+
+const static float3 colors[3] = {
+  float3(1.0, 1.0, 0.0),
+  float3(0.0, 1.0, 1.0),
+  float3(1.0, 0.0, 1.0)
+};
+
+struct Vertex
+{
+  float4 pos : SV_Position;
+  float3 color : Color;
+  int index : Index;
+  int value : Value;
+};
+
+const static uint MAX_VERTS = 12;
+const static uint MAX_PRIMS = 4;
+
+[outputtopology("triangle")]
+[numthreads(12, 1, 1)]
+void meshMain(
+    in uint tig : SV_GroupIndex,
+    out Vertices<Vertex, MAX_VERTS> verts,
+    out Indices<uint3, MAX_PRIMS> triangles)
+{
+    const uint numVertices = 12;
+    const uint numPrimitives = 4;
+    SetMeshOutputCounts(numVertices, numPrimitives);
+
+    if(tig < numVertices)
+    {
+        const int tri = tig / 3;
+        verts[tig] = {float4(positions[tig % 3], 0, 1), colors[tig % 3], tri, tri*tri};
+    }
+
+    if(tig < numPrimitives)
+        triangles[tig] = tig * 3 + uint3(0,1,2);
+}
+
+//
+// Fragment Shader
+//
+
+struct Fragment
+{
+    float4 color : SV_Target;
+};
+
+Fragment fragmentMain(Vertex input)
+{
+	outputBuffer[input.index] = input.value;
+
+	Fragment output;
+	output.color = float4(input.color, 1.0);
+	return output;
+}
diff --git a/tests/pipeline/rasterization/mesh/task-groupshared.slang b/tests/pipeline/rasterization/mesh/task-groupshared.slang
new file mode 100644
index 000000000..5690735cd
--- /dev/null
+++ b/tests/pipeline/rasterization/mesh/task-groupshared.slang
@@ -0,0 +1,109 @@
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHECK): -task -output-using-type -dx12 -use-dxil -profile sm_6_6 -render-features mesh-shader
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHECK): -task -output-using-type -vk -profile glsl_450+spirv_1_4 -render-features mesh-shader
+
+// Similar to task-simple, except that the payload is declared as a groupshared
+// variable. During lowerin to GLSL and SPIR-V we'll have to identify this as
+// the variable being passed to DispatchMesh and emit it using the
+// taskPayloadSharedEXT rate.
+
+// CHECK:      0
+// CHECK-NEXT: 1
+// CHECK-NEXT: 8
+// CHECK-NEXT: 27
+
+//TEST_INPUT: ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
+
+RWStructuredBuffer<float> outputBuffer;
+
+cbuffer Uniforms
+{
+    float4x4 modelViewProjection;
+}
+
+//
+// Task shader
+//
+
+struct MeshPayload
+{
+    int exponent;
+};
+
+groupshared MeshPayload p;
+
+[outputtopology("triangle")]
+[numthreads(1, 1, 1)]
+void taskMain(in uint tig : SV_GroupIndex)
+{
+    p.exponent = 3;
+    DispatchMesh(1,1,1,p);
+}
+
+
+//
+// Mesh shader
+//
+
+const static float2 positions[3] = {
+  float2(0.0, -0.5),
+  float2(0.5, 0.5),
+  float2(-0.5, 0.5)
+};
+
+const static float3 colors[3] = {
+  float3(1.0, 1.0, 0.0),
+  float3(0.0, 1.0, 1.0),
+  float3(1.0, 0.0, 1.0)
+};
+
+struct Vertex
+{
+  float4 pos : SV_Position;
+  float3 color : Color;
+  int index : Index;
+  int value : Value;
+};
+
+const static uint MAX_VERTS = 12;
+const static uint MAX_PRIMS = 4;
+
+[outputtopology("triangle")]
+[numthreads(12, 1, 1)]
+void meshMain(
+    in uint tig : SV_GroupIndex,
+    in payload MeshPayload meshPayload,
+    out Vertices<Vertex, MAX_VERTS> verts,
+    out Indices<uint3, MAX_PRIMS> triangles)
+{
+    const uint numVertices = 12;
+    const uint numPrimitives = 4;
+    SetMeshOutputCounts(numVertices, numPrimitives);
+
+    if(tig < numVertices)
+    {
+        const int tri = tig / 3;
+        verts[tig] = {float4(positions[tig % 3], 0, 1), colors[tig % 3], tri, int(pow(tri, meshPayload.exponent))};
+    }
+
+    if(tig < numPrimitives)
+        triangles[tig] = tig * 3 + uint3(0,1,2);
+}
+
+//
+// Fragment Shader
+//
+
+struct Fragment
+{
+    float4 color : SV_Target;
+};
+
+Fragment fragmentMain(Vertex input)
+{
+    outputBuffer[input.index] = input.value;
+
+    Fragment output;
+    output.color = float4(input.color, 1.0);
+    return output;
+}
+
diff --git a/tests/pipeline/rasterization/mesh/task-simple.slang b/tests/pipeline/rasterization/mesh/task-simple.slang
new file mode 100644
index 000000000..7da9ed32b
--- /dev/null
+++ b/tests/pipeline/rasterization/mesh/task-simple.slang
@@ -0,0 +1,106 @@
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHECK): -task -output-using-type -dx12 -use-dxil -profile sm_6_6 -render-features mesh-shader
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHECK): -task -output-using-type -vk -profile glsl_450+spirv_1_4 -render-features mesh-shader
+
+// To test a simple mesh shader, we'll generate 4 triangles, the vertices of
+// each one will hold the triangle index and a value (the square). The fragment
+// shader will write the value to the specified index of the output buffer.
+
+// CHECK:      0
+// CHECK-NEXT: 1
+// CHECK-NEXT: 8
+// CHECK-NEXT: 27
+
+//TEST_INPUT: ubuffer(data=[0 0 0 0], stride=4):out,name outputBuffer
+
+RWStructuredBuffer<float> outputBuffer;
+
+cbuffer Uniforms
+{
+	float4x4 modelViewProjection;
+}
+
+//
+// Task shader
+//
+
+struct MeshPayload
+{
+    int exponent;
+};
+
+[outputtopology("triangle")]
+[numthreads(1, 1, 1)]
+void taskMain(in uint tig : SV_GroupIndex)
+{
+    MeshPayload p;
+    p.exponent = 3;
+    DispatchMesh(1,1,1,p);
+}
+
+
+//
+// Mesh shader
+//
+
+const static float2 positions[3] = {
+  float2(0.0, -0.5),
+  float2(0.5, 0.5),
+  float2(-0.5, 0.5)
+};
+
+const static float3 colors[3] = {
+  float3(1.0, 1.0, 0.0),
+  float3(0.0, 1.0, 1.0),
+  float3(1.0, 0.0, 1.0)
+};
+
+struct Vertex
+{
+  float4 pos : SV_Position;
+  float3 color : Color;
+  int index : Index;
+  int value : Value;
+};
+
+const static uint MAX_VERTS = 12;
+const static uint MAX_PRIMS = 4;
+
+[outputtopology("triangle")]
+[numthreads(12, 1, 1)]
+void meshMain(
+    in uint tig : SV_GroupIndex,
+    in payload MeshPayload meshPayload,
+    out Vertices<Vertex, MAX_VERTS> verts,
+    out Indices<uint3, MAX_PRIMS> triangles)
+{
+    const uint numVertices = 12;
+    const uint numPrimitives = 4;
+    SetMeshOutputCounts(numVertices, numPrimitives);
+
+    if(tig < numVertices)
+    {
+        const int tri = tig / 3;
+        verts[tig] = {float4(positions[tig % 3], 0, 1), colors[tig % 3], tri, int(pow(tri, meshPayload.exponent))};
+    }
+
+    if(tig < numPrimitives)
+        triangles[tig] = tig * 3 + uint3(0,1,2);
+}
+
+//
+// Fragment Shader
+//
+
+struct Fragment
+{
+    float4 color : SV_Target;
+};
+
+Fragment fragmentMain(Vertex input)
+{
+	outputBuffer[input.index] = input.value;
+
+	Fragment output;
+	output.color = float4(input.color, 1.0);
+	return output;
+}