[DirectX] Implement Max64UAVs shader flag analysis

llvm/lib/Target/DirectX/DXILShaderFlags.cpp

@@ -255,6 +255,16 @@ void ModuleShaderFlags::initialize(Module &M, DXILResourceTypeMap &DRTM,
         EntryFunProps.Entry->getContext().diagnose(DiagnosticInfoUnsupported(
             *(EntryFunProps.Entry), "Inconsistent optnone attribute "));
   }
+
+  // Set the Max64UAVs flag if the number of UAVs is > 8
+  uint32_t NumUAVs = 0;
+  for (auto &UAV : DRM.uavs())
+    if (MMDI.DXILVersion < VersionTuple(1, 6))
+      NumUAVs++;
+    else // MMDI.DXILVersion >= VersionTuple(1, 6)
+      NumUAVs += UAV.getBinding().Size;
+  if (NumUAVs > 8)
+    CombinedSFMask.Max64UAVs = true;
 }
 
 void ComputedShaderFlags::print(raw_ostream &OS) const {

llvm/test/CodeGen/DirectX/ShaderFlags/max-64-uavs-array-sm6_5.ll

@@ -0,0 +1,33 @@
+; RUN: opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s
+
+; This test makes sure that resource arrays only add 1 to the count of the
+; number of UAVs for setting the shader flag '64 UAV slots' when the shader
+; model version is < 6.6
+
+; Note: there is no feature flag here (only a module flag), so we don't have an
+; object test.
+
+target triple = "dxil-pc-shadermodel6.5-library"
+
+; CHECK:      Combined Shader Flags for Module
+; CHECK-NEXT: Shader Flags Value: 0x00000000
+
+; CHECK-NOT: Note: shader requires additional functionality:
+; CHECK-NOT:    64 UAV slots
+
+; CHECK: Function test : 0x00000000
+define void @test() "hlsl.export" {
+  ; RWBuffer<float> Buf : register(u0, space0)
+  %buf0 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 0, i32 1, i32 0, i1 false)
+
+  ; RWBuffer<float> Buf[8] : register(u1, space0)
+  %buf1 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 1, i32 8, i32 0, i1 false)
+  ret void
+}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"dx.resmayalias", i32 1}

llvm/test/CodeGen/DirectX/ShaderFlags/max-64-uavs-array-sm6_6.ll

@@ -0,0 +1,33 @@
+; RUN: opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s
+
+; This test makes sure that resource arrays sizes are accounted for when
+; counting the number of UAVs for setting the shader flag '64 UAV slots' when
+; the shader model version is >= 6.6
+
+; Note: there is no feature flag here (only a module flag), so we don't have an
+; object test.
+
+target triple = "dxil-pc-shadermodel6.6-library"
+
+; CHECK:      Combined Shader Flags for Module
+; CHECK-NEXT: Shader Flags Value: 0x00008000
+
+; CHECK: Note: shader requires additional functionality:
+; CHECK:        64 UAV slots
+
+; CHECK: Function test : 0x00000000
+define void @test() "hlsl.export" {
+  ; RWBuffer<float> Buf : register(u0, space0)
+  %buf0 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 0, i32 1, i32 0, i1 false)
+
+  ; RWBuffer<float> Buf[8] : register(u1, space0)
+  %buf1 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 1, i32 8, i32 0, i1 false)
+  ret void
+}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"dx.resmayalias", i32 1}

llvm/test/CodeGen/DirectX/ShaderFlags/max-64-uavs.ll

@@ -0,0 +1,60 @@
+; RUN: opt -S --passes="print-dx-shader-flags" 2>&1 %s | FileCheck %s
+
+; This test makes sure that the shader flag '64 UAV slots' is set when there are
+; more than 8 UAVs in the module.
+
+; Note: there is no feature flag here (only a module flag), so we don't have an
+; object test.
+
+target triple = "dxil-pc-shadermodel6.7-library"
+
+; CHECK:      Combined Shader Flags for Module
+; CHECK-NEXT: Shader Flags Value: 0x00008000
+
+; CHECK: Note: shader requires additional functionality:
+; CHECK:       64 UAV slots
+
+; Note: 64 UAV slots does not get set per-function
+; CHECK: Function test : 0x00000000
+define void @test() "hlsl.export" {
+  ; RWBuffer<float> Buf : register(u0, space0)
+  %buf0 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 0, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u1, space0)
+  %buf1 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 1, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u2, space0)
+  %buf2 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 2, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u3, space0)
+  %buf3 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 3, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u4, space0)
+  %buf4 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 4, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u5, space0)
+  %buf5 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 5, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u6, space0)
+  %buf6 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 6, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u7, space0)
+  %buf7 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 7, i32 1, i32 0, i1 false)
+  ; RWBuffer<float> Buf : register(u8, space0)
+  %buf8 = call target("dx.TypedBuffer", float, 1, 0, 1)
+       @llvm.dx.resource.handlefrombinding.tdx.TypedBuffer_f32_1_0t(
+           i32 0, i32 8, i32 1, i32 0, i1 false)
+  ret void
+}
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 1, !"dx.resmayalias", i32 1}