https://github.com/bogner updated
https://github.com/llvm/llvm-project/pull/140315
>From e4d7bfd8226d730fc8c12e5af765f22069a0d8bf Mon Sep 17 00:00:00 2001
From: Justin Bogner <m...@justinbogner.com>
Date: Wed, 7 May 2025 16:11:28 -0700
Subject: [PATCH 1/2] [DirectX][SPIRV] Fix the lowering of dot4add
There were some issues with these ops:
- The overload wasn't being specified (`dx.op.dot4AddPacked` vs
`dx.op.dot4AddPacked.i32`)
- The versioning wasn't correct (These ops were added in SM 6.4)
- The argument order was off - while the HLSL function has the
accumulator as the last argument, the DXIL op lists it first.
This fixes the DXIL.td definition and adjusts the LLVM DX and SPIRV
intrinsics to match the argument order in DXIL rather than the argument
order in HLSL.
Fixes #139018
---
clang/lib/CodeGen/CGHLSLBuiltins.cpp | 24 ++++++-----
.../builtins/dot4add_i8packed.hlsl | 26 ++++++------
.../builtins/dot4add_u8packed.hlsl | 29 +++++++-------
llvm/lib/Target/DirectX/DXIL.td | 14 ++++---
.../Target/SPIRV/SPIRVInstructionSelector.cpp | 20 ++++++----
llvm/test/CodeGen/DirectX/dot4add_i8packed.ll | 8 ++--
.../CodeGen/DirectX/dot4add_i8packed_error.ll | 10 +++++
llvm/test/CodeGen/DirectX/dot4add_u8packed.ll | 8 ++--
.../CodeGen/DirectX/dot4add_u8packed_error.ll | 10 +++++
.../SPIRV/hlsl-intrinsics/dot4add_i8packed.ll | 40 +++++++++----------
.../SPIRV/hlsl-intrinsics/dot4add_u8packed.ll | 40 +++++++++----------
11 files changed, 132 insertions(+), 97 deletions(-)
create mode 100644 llvm/test/CodeGen/DirectX/dot4add_i8packed_error.ll
create mode 100644 llvm/test/CodeGen/DirectX/dot4add_u8packed_error.ll
diff --git a/clang/lib/CodeGen/CGHLSLBuiltins.cpp
b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
index d4a0714da07b3..08eec6d5a2845 100644
--- a/clang/lib/CodeGen/CGHLSLBuiltins.cpp
+++ b/clang/lib/CodeGen/CGHLSLBuiltins.cpp
@@ -412,24 +412,28 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned
BuiltinID,
ArrayRef<Value *>{Op0, Op1}, nullptr, "hlsl.dot");
}
case Builtin::BI__builtin_hlsl_dot4add_i8packed: {
- Value *A = EmitScalarExpr(E->getArg(0));
- Value *B = EmitScalarExpr(E->getArg(1));
- Value *C = EmitScalarExpr(E->getArg(2));
+ Value *X = EmitScalarExpr(E->getArg(0));
+ Value *Y = EmitScalarExpr(E->getArg(1));
+ Value *Acc = EmitScalarExpr(E->getArg(2));
Intrinsic::ID ID = CGM.getHLSLRuntime().getDot4AddI8PackedIntrinsic();
+ // Note that the argument order disagrees between the builtin and the
+ // intrinsic here.
return Builder.CreateIntrinsic(
- /*ReturnType=*/C->getType(), ID, ArrayRef<Value *>{A, B, C}, nullptr,
- "hlsl.dot4add.i8packed");
+ /*ReturnType=*/Acc->getType(), ID, ArrayRef<Value *>{Acc, X, Y},
+ nullptr, "hlsl.dot4add.i8packed");
}
case Builtin::BI__builtin_hlsl_dot4add_u8packed: {
- Value *A = EmitScalarExpr(E->getArg(0));
- Value *B = EmitScalarExpr(E->getArg(1));
- Value *C = EmitScalarExpr(E->getArg(2));
+ Value *X = EmitScalarExpr(E->getArg(0));
+ Value *Y = EmitScalarExpr(E->getArg(1));
+ Value *Acc = EmitScalarExpr(E->getArg(2));
Intrinsic::ID ID = CGM.getHLSLRuntime().getDot4AddU8PackedIntrinsic();
+ // Note that the argument order disagrees between the builtin and the
+ // intrinsic here.
return Builder.CreateIntrinsic(
- /*ReturnType=*/C->getType(), ID, ArrayRef<Value *>{A, B, C}, nullptr,
- "hlsl.dot4add.u8packed");
+ /*ReturnType=*/Acc->getType(), ID, ArrayRef<Value *>{Acc, X, Y},
+ nullptr, "hlsl.dot4add.u8packed");
}
case Builtin::BI__builtin_hlsl_elementwise_firstbithigh: {
Value *X = EmitScalarExpr(E->getArg(0));
diff --git a/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
b/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
index 7cc31512844d1..fd9ded6a5d6bf 100644
--- a/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
+++ b/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
@@ -1,17 +1,19 @@
-// RUN: %clang_cc1 -finclude-default-header -triple \
-// RUN: dxil-pc-shadermodel6.3-compute %s -emit-llvm -disable-llvm-passes -o
- | \
-// RUN: FileCheck %s -DTARGET=dx
-// RUN: %clang_cc1 -finclude-default-header -triple \
-// RUN: spirv-pc-vulkan-compute %s -emit-llvm -disable-llvm-passes -o - | \
-// RUN: FileCheck %s -DTARGET=spv
+// RUN: %clang_cc1 -finclude-default-header -triple
dxil-pc-shadermodel6.3-compute %s -emit-llvm -o - | FileCheck %s -DTARGET=dx
+// RUN: %clang_cc1 -finclude-default-header -triple spirv-pc-vulkan-compute %s
-emit-llvm -o - | FileCheck %s -DTARGET=spv
// Test basic lowering to runtime function call.
// CHECK-LABEL: test
-int test(uint a, uint b, int c) {
- // CHECK: %[[RET:.*]] = call [[TY:i32]]
@llvm.[[TARGET]].dot4add.i8packed([[TY]] %[[#]], [[TY]] %[[#]], [[TY]] %[[#]])
- // CHECK: ret [[TY]] %[[RET]]
- return dot4add_i8packed(a, b, c);
+int test(uint x, uint y, int acc) {
+ // CHECK: [[X_ADDR:%.*]] = alloca i32, align 4
+ // CHECK: [[Y_ADDR:%.*]] = alloca i32, align 4
+ // CHECK: [[ACC_ADDR:%.*]] = alloca i32, align 4
+ // CHECK: store i32 %x, ptr [[X_ADDR]], align 4
+ // CHECK: store i32 %y, ptr [[Y_ADDR]], align 4
+ // CHECK: store i32 %acc, ptr [[ACC_ADDR]], align 4
+ // CHECK: [[X0:%.*]] = load i32, ptr [[X_ADDR]], align 4
+ // CHECK: [[Y0:%.*]] = load i32, ptr [[Y_ADDR]], align 4
+ // CHECK: [[ACC0:%.*]] = load i32, ptr [[ACC_ADDR]], align 4
+ // CHECK: call i32 @llvm.[[TARGET]].dot4add.i8packed(i32 [[ACC0]], i32
[[X0]], i32 [[Y0]])
+ return dot4add_i8packed(x, y, acc);
}
-
-// CHECK: declare [[TY]] @llvm.[[TARGET]].dot4add.i8packed([[TY]], [[TY]],
[[TY]])
diff --git a/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
b/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
index c388cf58cd17c..34f80a5ed1f57 100644
--- a/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
+++ b/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
@@ -1,18 +1,19 @@
-
-// RUN: %clang_cc1 -finclude-default-header -triple \
-// RUN: dxil-pc-shadermodel6.3-compute %s -emit-llvm -disable-llvm-passes -o
- | \
-// RUN: FileCheck %s -DTARGET=dx
-// RUN: %clang_cc1 -finclude-default-header -triple \
-// RUN: spirv-pc-vulkan-compute %s -emit-llvm -disable-llvm-passes -o - | \
-// RUN: FileCheck %s -DTARGET=spv
+// RUN: %clang_cc1 -finclude-default-header -triple
dxil-pc-shadermodel6.3-compute %s -emit-llvm -o - | FileCheck %s -DTARGET=dx
+// RUN: %clang_cc1 -finclude-default-header -triple spirv-pc-vulkan-compute %s
-emit-llvm -o - | FileCheck %s -DTARGET=spv
// Test basic lowering to runtime function call.
-// CHECK-LABEL: define {{.*}}test
-uint test(uint a, uint b, uint c) {
- // CHECK: %[[RET:.*]] = call [[TY:i32]]
@llvm.[[TARGET]].dot4add.u8packed([[TY]] %[[#]], [[TY]] %[[#]], [[TY]] %[[#]])
- // CHECK: ret [[TY]] %[[RET]]
- return dot4add_u8packed(a, b, c);
+// CHECK-LABEL: test
+int test(uint x, uint y, int acc) {
+ // CHECK: [[X_ADDR:%.*]] = alloca i32, align 4
+ // CHECK: [[Y_ADDR:%.*]] = alloca i32, align 4
+ // CHECK: [[ACC_ADDR:%.*]] = alloca i32, align 4
+ // CHECK: store i32 %x, ptr [[X_ADDR]], align 4
+ // CHECK: store i32 %y, ptr [[Y_ADDR]], align 4
+ // CHECK: store i32 %acc, ptr [[ACC_ADDR]], align 4
+ // CHECK: [[X0:%.*]] = load i32, ptr [[X_ADDR]], align 4
+ // CHECK: [[Y0:%.*]] = load i32, ptr [[Y_ADDR]], align 4
+ // CHECK: [[ACC0:%.*]] = load i32, ptr [[ACC_ADDR]], align 4
+ // CHECK: call i32 @llvm.[[TARGET]].dot4add.u8packed(i32 [[ACC0]], i32
[[X0]], i32 [[Y0]])
+ return dot4add_u8packed(x, y, acc);
}
-
-// CHECK: declare [[TY]] @llvm.[[TARGET]].dot4add.u8packed([[TY]], [[TY]],
[[TY]])
diff --git a/llvm/lib/Target/DirectX/DXIL.td b/llvm/lib/Target/DirectX/DXIL.td
index b3b3bcdba491a..fd4f90c8a7fd4 100644
--- a/llvm/lib/Target/DirectX/DXIL.td
+++ b/llvm/lib/Target/DirectX/DXIL.td
@@ -1119,9 +1119,10 @@ def Dot4AddI8Packed : DXILOp<163, dot4AddPacked> {
"accumulate to i32";
let intrinsics = [IntrinSelect<int_dx_dot4add_i8packed>];
let arguments = [Int32Ty, Int32Ty, Int32Ty];
- let result = Int32Ty;
- let stages = [Stages<DXIL1_0, [all_stages]>];
- let attributes = [Attributes<DXIL1_0, [ReadNone]>];
+ let result = OverloadTy;
+ let overloads = [Overloads<DXIL1_4, [Int32Ty]>];
+ let stages = [Stages<DXIL1_4, [all_stages]>];
+ let attributes = [Attributes<DXIL1_4, [ReadNone]>];
}
def Dot4AddU8Packed : DXILOp<164, dot4AddPacked> {
@@ -1129,9 +1130,10 @@ def Dot4AddU8Packed : DXILOp<164, dot4AddPacked> {
"accumulate to i32";
let intrinsics = [IntrinSelect<int_dx_dot4add_u8packed>];
let arguments = [Int32Ty, Int32Ty, Int32Ty];
- let result = Int32Ty;
- let stages = [Stages<DXIL1_0, [all_stages]>];
- let attributes = [Attributes<DXIL1_0, [ReadNone]>];
+ let result = OverloadTy;
+ let overloads = [Overloads<DXIL1_4, [Int32Ty]>];
+ let stages = [Stages<DXIL1_4, [all_stages]>];
+ let attributes = [Attributes<DXIL1_4, [ReadNone]>];
}
def AnnotateHandle : DXILOp<216, annotateHandle> {
diff --git a/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
b/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
index 0db60c068bdff..73e5e1ef36a5b 100644
--- a/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
+++ b/llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
@@ -2021,20 +2021,24 @@ bool
SPIRVInstructionSelector::selectDot4AddPacked(Register ResVReg,
assert(I.getOperand(4).isReg());
MachineBasicBlock &BB = *I.getParent();
+ Register Acc = I.getOperand(2).getReg();
+ Register X = I.getOperand(3).getReg();
+ Register Y = I.getOperand(4).getReg();
+
auto DotOp = Signed ? SPIRV::OpSDot : SPIRV::OpUDot;
Register Dot = MRI->createVirtualRegister(GR.getRegClass(ResType));
bool Result = BuildMI(BB, I, I.getDebugLoc(), TII.get(DotOp))
.addDef(Dot)
.addUse(GR.getSPIRVTypeID(ResType))
- .addUse(I.getOperand(2).getReg())
- .addUse(I.getOperand(3).getReg())
+ .addUse(X)
+ .addUse(Y)
.constrainAllUses(TII, TRI, RBI);
return Result && BuildMI(BB, I, I.getDebugLoc(), TII.get(SPIRV::OpIAddS))
.addDef(ResVReg)
.addUse(GR.getSPIRVTypeID(ResType))
.addUse(Dot)
- .addUse(I.getOperand(4).getReg())
+ .addUse(Acc)
.constrainAllUses(TII, TRI, RBI);
}
@@ -2052,8 +2056,10 @@ bool
SPIRVInstructionSelector::selectDot4AddPackedExpansion(
bool Result = true;
- // Acc = C
- Register Acc = I.getOperand(4).getReg();
+ Register Acc = I.getOperand(2).getReg();
+ Register X = I.getOperand(3).getReg();
+ Register Y = I.getOperand(4).getReg();
+
SPIRVType *EltType = GR.getOrCreateSPIRVIntegerType(8, I, TII);
auto ExtractOp =
Signed ? SPIRV::OpBitFieldSExtract : SPIRV::OpBitFieldUExtract;
@@ -2067,7 +2073,7 @@ bool
SPIRVInstructionSelector::selectDot4AddPackedExpansion(
BuildMI(BB, I, I.getDebugLoc(), TII.get(ExtractOp))
.addDef(AElt)
.addUse(GR.getSPIRVTypeID(ResType))
- .addUse(I.getOperand(2).getReg())
+ .addUse(X)
.addUse(GR.getOrCreateConstInt(i * 8, I, EltType, TII, ZeroAsNull))
.addUse(GR.getOrCreateConstInt(8, I, EltType, TII, ZeroAsNull))
.constrainAllUses(TII, TRI, RBI);
@@ -2078,7 +2084,7 @@ bool
SPIRVInstructionSelector::selectDot4AddPackedExpansion(
BuildMI(BB, I, I.getDebugLoc(), TII.get(ExtractOp))
.addDef(BElt)
.addUse(GR.getSPIRVTypeID(ResType))
- .addUse(I.getOperand(3).getReg())
+ .addUse(Y)
.addUse(GR.getOrCreateConstInt(i * 8, I, EltType, TII, ZeroAsNull))
.addUse(GR.getOrCreateConstInt(8, I, EltType, TII, ZeroAsNull))
.constrainAllUses(TII, TRI, RBI);
diff --git a/llvm/test/CodeGen/DirectX/dot4add_i8packed.ll
b/llvm/test/CodeGen/DirectX/dot4add_i8packed.ll
index 63d2873cb46e2..1786b0238dc2b 100644
--- a/llvm/test/CodeGen/DirectX/dot4add_i8packed.ll
+++ b/llvm/test/CodeGen/DirectX/dot4add_i8packed.ll
@@ -1,9 +1,9 @@
-; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-compute %s |
FileCheck %s
+; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.4-compute %s |
FileCheck %s
-define void @main(i32 %a, i32 %b, i32 %c) {
+define void @main(i32 %acc, i32 %x, i32 %y) {
entry:
-; CHECK: call i32 @dx.op.dot4AddPacked(i32 163, i32 %a, i32 %b, i32 %c)
#[[#ATTR:]]
- %0 = call i32 @llvm.dx.dot4add.i8packed(i32 %a, i32 %b, i32 %c)
+; CHECK: call i32 @dx.op.dot4AddPacked.i32(i32 163, i32 %acc, i32 %x, i32 %y)
#[[#ATTR:]]
+ %0 = call i32 @llvm.dx.dot4add.i8packed(i32 %acc, i32 %x, i32 %y)
ret void
}
diff --git a/llvm/test/CodeGen/DirectX/dot4add_i8packed_error.ll
b/llvm/test/CodeGen/DirectX/dot4add_i8packed_error.ll
new file mode 100644
index 0000000000000..f600be0d0960a
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/dot4add_i8packed_error.ll
@@ -0,0 +1,10 @@
+; RUN: not opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-compute %s
2>&1 | FileCheck %s
+
+; CHECK: in function f
+; CHECK-SAME: Cannot create Dot4AddI8Packed operation: No valid overloads for
DXIL version 1.3
+
+define void @f(i32 %acc, i32 %x, i32 %y) {
+entry:
+ %0 = call i32 @llvm.dx.dot4add.i8packed(i32 %acc, i32 %x, i32 %y)
+ ret void
+}
diff --git a/llvm/test/CodeGen/DirectX/dot4add_u8packed.ll
b/llvm/test/CodeGen/DirectX/dot4add_u8packed.ll
index a9828bafddaab..776fae7f98c2a 100644
--- a/llvm/test/CodeGen/DirectX/dot4add_u8packed.ll
+++ b/llvm/test/CodeGen/DirectX/dot4add_u8packed.ll
@@ -1,9 +1,9 @@
-; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-compute %s |
FileCheck %s
+; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.4-compute %s |
FileCheck %s
-define void @main(i32 %a, i32 %b, i32 %c) {
+define void @main(i32 %acc, i32 %x, i32 %y) {
entry:
-; CHECK: call i32 @dx.op.dot4AddPacked(i32 164, i32 %a, i32 %b, i32 %c)
#[[#ATTR:]]
- %0 = call i32 @llvm.dx.dot4add.u8packed(i32 %a, i32 %b, i32 %c)
+; CHECK: call i32 @dx.op.dot4AddPacked.i32(i32 164, i32 %acc, i32 %x, i32 %y)
#[[#ATTR:]]
+ %0 = call i32 @llvm.dx.dot4add.u8packed(i32 %acc, i32 %x, i32 %y)
ret void
}
diff --git a/llvm/test/CodeGen/DirectX/dot4add_u8packed_error.ll
b/llvm/test/CodeGen/DirectX/dot4add_u8packed_error.ll
new file mode 100644
index 0000000000000..8ccd814b4847b
--- /dev/null
+++ b/llvm/test/CodeGen/DirectX/dot4add_u8packed_error.ll
@@ -0,0 +1,10 @@
+; RUN: not opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-compute %s
2>&1 | FileCheck %s
+
+; CHECK: in function f
+; CHECK-SAME: Cannot create Dot4AddU8Packed operation: No valid overloads for
DXIL version 1.3
+
+define void @f(i32 %acc, i32 %x, i32 %y) {
+entry:
+ %0 = call i32 @llvm.dx.dot4add.u8packed(i32 %acc, i32 %x, i32 %y)
+ ret void
+}
diff --git a/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_i8packed.ll
b/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_i8packed.ll
index 8715fc324c071..222aca53ab6ac 100644
--- a/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_i8packed.ll
+++ b/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_i8packed.ll
@@ -17,49 +17,49 @@
; CHECK-EXP-DAG: %[[#twentyfour:]] = OpConstant %[[#int_8]] 24
; CHECK-LABEL: Begin function test_dot
-define noundef i32 @test_dot(i32 noundef %a, i32 noundef %b, i32 noundef %c) {
+define noundef i32 @test_dot(i32 noundef %acc, i32 noundef %x, i32 noundef %y)
{
entry:
-; CHECK: %[[#A:]] = OpFunctionParameter %[[#int_32]]
-; CHECK: %[[#B:]] = OpFunctionParameter %[[#int_32]]
-; CHECK: %[[#C:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#ACC:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#X:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#Y:]] = OpFunctionParameter %[[#int_32]]
; Test that we use the dot product op when capabilities allow
-; CHECK-DOT: %[[#DOT:]] = OpSDot %[[#int_32]] %[[#A]] %[[#B]]
-; CHECK-DOT: %[[#RES:]] = OpIAdd %[[#int_32]] %[[#DOT]] %[[#C]]
+; CHECK-DOT: %[[#DOT:]] = OpSDot %[[#int_32]] %[[#X]] %[[#Y]]
+; CHECK-DOT: %[[#RES:]] = OpIAdd %[[#int_32]] %[[#DOT]] %[[#ACC]]
; Test expansion is used when spirv dot product capabilities aren't available:
; First element of the packed vector
-; CHECK-EXP: %[[#A0:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]] %[[#zero]]
%[[#eight]]
-; CHECK-EXP: %[[#B0:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]] %[[#zero]]
%[[#eight]]
-; CHECK-EXP: %[[#MUL0:]] = OpIMul %[[#int_32]] %[[#A0]] %[[#B0]]
+; CHECK-EXP: %[[#X0:]] = OpBitFieldSExtract %[[#int_32]] %[[#X]] %[[#zero]]
%[[#eight]]
+; CHECK-EXP: %[[#Y0:]] = OpBitFieldSExtract %[[#int_32]] %[[#Y]] %[[#zero]]
%[[#eight]]
+; CHECK-EXP: %[[#MUL0:]] = OpIMul %[[#int_32]] %[[#X0]] %[[#Y0]]
; CHECK-EXP: %[[#MASK0:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL0]]
%[[#zero]] %[[#eight]]
-; CHECK-EXP: %[[#ACC0:]] = OpIAdd %[[#int_32]] %[[#C]] %[[#MASK0]]
+; CHECK-EXP: %[[#ACC0:]] = OpIAdd %[[#int_32]] %[[#ACC]] %[[#MASK0]]
; Second element of the packed vector
-; CHECK-EXP: %[[#A1:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]] %[[#eight]]
%[[#eight]]
-; CHECK-EXP: %[[#B1:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]] %[[#eight]]
%[[#eight]]
-; CHECK-EXP: %[[#MUL1:]] = OpIMul %[[#int_32]] %[[#A1]] %[[#B1]]
+; CHECK-EXP: %[[#X1:]] = OpBitFieldSExtract %[[#int_32]] %[[#X]] %[[#eight]]
%[[#eight]]
+; CHECK-EXP: %[[#Y1:]] = OpBitFieldSExtract %[[#int_32]] %[[#Y]] %[[#eight]]
%[[#eight]]
+; CHECK-EXP: %[[#MUL1:]] = OpIMul %[[#int_32]] %[[#X1]] %[[#Y1]]
; CHECK-EXP: %[[#MASK1:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL1]]
%[[#zero]] %[[#eight]]
; CHECK-EXP: %[[#ACC1:]] = OpIAdd %[[#int_32]] %[[#ACC0]] %[[#MASK1]]
; Third element of the packed vector
-; CHECK-EXP: %[[#A2:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]] %[[#sixteen]]
%[[#eight]]
-; CHECK-EXP: %[[#B2:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]] %[[#sixteen]]
%[[#eight]]
-; CHECK-EXP: %[[#MUL2:]] = OpIMul %[[#int_32]] %[[#A2]] %[[#B2]]
+; CHECK-EXP: %[[#X2:]] = OpBitFieldSExtract %[[#int_32]] %[[#X]] %[[#sixteen]]
%[[#eight]]
+; CHECK-EXP: %[[#Y2:]] = OpBitFieldSExtract %[[#int_32]] %[[#Y]] %[[#sixteen]]
%[[#eight]]
+; CHECK-EXP: %[[#MUL2:]] = OpIMul %[[#int_32]] %[[#X2]] %[[#Y2]]
; CHECK-EXP: %[[#MASK2:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL2]]
%[[#zero]] %[[#eight]]
; CHECK-EXP: %[[#ACC2:]] = OpIAdd %[[#int_32]] %[[#ACC1]] %[[#MASK2]]
; Fourth element of the packed vector
-; CHECK-EXP: %[[#A3:]] = OpBitFieldSExtract %[[#int_32]] %[[#A]]
%[[#twentyfour]] %[[#eight]]
-; CHECK-EXP: %[[#B3:]] = OpBitFieldSExtract %[[#int_32]] %[[#B]]
%[[#twentyfour]] %[[#eight]]
-; CHECK-EXP: %[[#MUL3:]] = OpIMul %[[#int_32]] %[[#A3]] %[[#B3]]
+; CHECK-EXP: %[[#X3:]] = OpBitFieldSExtract %[[#int_32]] %[[#X]]
%[[#twentyfour]] %[[#eight]]
+; CHECK-EXP: %[[#Y3:]] = OpBitFieldSExtract %[[#int_32]] %[[#Y]]
%[[#twentyfour]] %[[#eight]]
+; CHECK-EXP: %[[#MUL3:]] = OpIMul %[[#int_32]] %[[#X3]] %[[#Y3]]
; CHECK-EXP: %[[#MASK3:]] = OpBitFieldSExtract %[[#int_32]] %[[#MUL3]]
%[[#zero]] %[[#eight]]
; CHECK-EXP: %[[#RES:]] = OpIAdd %[[#int_32]] %[[#ACC2]] %[[#MASK3]]
; CHECK: OpReturnValue %[[#RES]]
- %spv.dot = call i32 @llvm.spv.dot4add.i8packed(i32 %a, i32 %b, i32 %c)
+ %spv.dot = call i32 @llvm.spv.dot4add.i8packed(i32 %acc, i32 %x, i32 %y)
ret i32 %spv.dot
}
diff --git a/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_u8packed.ll
b/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_u8packed.ll
index a43d0be9e775b..616f4cc019785 100644
--- a/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_u8packed.ll
+++ b/llvm/test/CodeGen/SPIRV/hlsl-intrinsics/dot4add_u8packed.ll
@@ -17,49 +17,49 @@
; CHECK-EXP-DAG: %[[#twentyfour:]] = OpConstant %[[#int_8]] 24
; CHECK-LABEL: Begin function test_dot
-define noundef i32 @test_dot(i32 noundef %a, i32 noundef %b, i32 noundef %c) {
+define noundef i32 @test_dot(i32 noundef %acc, i32 noundef %x, i32 noundef %y)
{
entry:
-; CHECK: %[[#A:]] = OpFunctionParameter %[[#int_32]]
-; CHECK: %[[#B:]] = OpFunctionParameter %[[#int_32]]
-; CHECK: %[[#C:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#ACC:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#X:]] = OpFunctionParameter %[[#int_32]]
+; CHECK: %[[#Y:]] = OpFunctionParameter %[[#int_32]]
; Test that we use the dot product op when capabilities allow
-; CHECK-DOT: %[[#DOT:]] = OpUDot %[[#int_32]] %[[#A]] %[[#B]]
-; CHECK-DOT: %[[#RES:]] = OpIAdd %[[#int_32]] %[[#DOT]] %[[#C]]
+; CHECK-DOT: %[[#DOT:]] = OpUDot %[[#int_32]] %[[#X]] %[[#Y]]
+; CHECK-DOT: %[[#RES:]] = OpIAdd %[[#int_32]] %[[#DOT]] %[[#ACC]]
; Test expansion is used when spirv dot product capabilities aren't available:
; First element of the packed vector
-; CHECK-EXP: %[[#A0:]] = OpBitFieldUExtract %[[#int_32]] %[[#A]] %[[#zero]]
%[[#eight]]
-; CHECK-EXP: %[[#B0:]] = OpBitFieldUExtract %[[#int_32]] %[[#B]] %[[#zero]]
%[[#eight]]
-; CHECK-EXP: %[[#MUL0:]] = OpIMul %[[#int_32]] %[[#A0]] %[[#B0]]
+; CHECK-EXP: %[[#X0:]] = OpBitFieldUExtract %[[#int_32]] %[[#X]] %[[#zero]]
%[[#eight]]
+; CHECK-EXP: %[[#Y0:]] = OpBitFieldUExtract %[[#int_32]] %[[#Y]] %[[#zero]]
%[[#eight]]
+; CHECK-EXP: %[[#MUL0:]] = OpIMul %[[#int_32]] %[[#X0]] %[[#Y0]]
; CHECK-EXP: %[[#MASK0:]] = OpBitFieldUExtract %[[#int_32]] %[[#MUL0]]
%[[#zero]] %[[#eight]]
-; CHECK-EXP: %[[#ACC0:]] = OpIAdd %[[#int_32]] %[[#C]] %[[#MASK0]]
+; CHECK-EXP: %[[#ACC0:]] = OpIAdd %[[#int_32]] %[[#ACC]] %[[#MASK0]]
; Second element of the packed vector
-; CHECK-EXP: %[[#A1:]] = OpBitFieldUExtract %[[#int_32]] %[[#A]] %[[#eight]]
%[[#eight]]
-; CHECK-EXP: %[[#B1:]] = OpBitFieldUExtract %[[#int_32]] %[[#B]] %[[#eight]]
%[[#eight]]
-; CHECK-EXP: %[[#MUL1:]] = OpIMul %[[#int_32]] %[[#A1]] %[[#B1]]
+; CHECK-EXP: %[[#X1:]] = OpBitFieldUExtract %[[#int_32]] %[[#X]] %[[#eight]]
%[[#eight]]
+; CHECK-EXP: %[[#Y1:]] = OpBitFieldUExtract %[[#int_32]] %[[#Y]] %[[#eight]]
%[[#eight]]
+; CHECK-EXP: %[[#MUL1:]] = OpIMul %[[#int_32]] %[[#X1]] %[[#Y1]]
; CHECK-EXP: %[[#MASK1:]] = OpBitFieldUExtract %[[#int_32]] %[[#MUL1]]
%[[#zero]] %[[#eight]]
; CHECK-EXP: %[[#ACC1:]] = OpIAdd %[[#int_32]] %[[#ACC0]] %[[#MASK1]]
; Third element of the packed vector
-; CHECK-EXP: %[[#A2:]] = OpBitFieldUExtract %[[#int_32]] %[[#A]] %[[#sixteen]]
%[[#eight]]
-; CHECK-EXP: %[[#B2:]] = OpBitFieldUExtract %[[#int_32]] %[[#B]] %[[#sixteen]]
%[[#eight]]
-; CHECK-EXP: %[[#MUL2:]] = OpIMul %[[#int_32]] %[[#A2]] %[[#B2]]
+; CHECK-EXP: %[[#X2:]] = OpBitFieldUExtract %[[#int_32]] %[[#X]] %[[#sixteen]]
%[[#eight]]
+; CHECK-EXP: %[[#Y2:]] = OpBitFieldUExtract %[[#int_32]] %[[#Y]] %[[#sixteen]]
%[[#eight]]
+; CHECK-EXP: %[[#MUL2:]] = OpIMul %[[#int_32]] %[[#X2]] %[[#Y2]]
; CHECK-EXP: %[[#MASK2:]] = OpBitFieldUExtract %[[#int_32]] %[[#MUL2]]
%[[#zero]] %[[#eight]]
; CHECK-EXP: %[[#ACC2:]] = OpIAdd %[[#int_32]] %[[#ACC1]] %[[#MASK2]]
; Fourth element of the packed vector
-; CHECK-EXP: %[[#A3:]] = OpBitFieldUExtract %[[#int_32]] %[[#A]]
%[[#twentyfour]] %[[#eight]]
-; CHECK-EXP: %[[#B3:]] = OpBitFieldUExtract %[[#int_32]] %[[#B]]
%[[#twentyfour]] %[[#eight]]
-; CHECK-EXP: %[[#MUL3:]] = OpIMul %[[#int_32]] %[[#A3]] %[[#B3]]
+; CHECK-EXP: %[[#X3:]] = OpBitFieldUExtract %[[#int_32]] %[[#X]]
%[[#twentyfour]] %[[#eight]]
+; CHECK-EXP: %[[#Y3:]] = OpBitFieldUExtract %[[#int_32]] %[[#Y]]
%[[#twentyfour]] %[[#eight]]
+; CHECK-EXP: %[[#MUL3:]] = OpIMul %[[#int_32]] %[[#X3]] %[[#Y3]]
; CHECK-EXP: %[[#MASK3:]] = OpBitFieldUExtract %[[#int_32]] %[[#MUL3]]
%[[#zero]] %[[#eight]]
; CHECK-EXP: %[[#RES:]] = OpIAdd %[[#int_32]] %[[#ACC2]] %[[#MASK3]]
; CHECK: OpReturnValue %[[#RES]]
- %spv.dot = call i32 @llvm.spv.dot4add.u8packed(i32 %a, i32 %b, i32 %c)
+ %spv.dot = call i32 @llvm.spv.dot4add.u8packed(i32 %acc, i32 %x, i32 %y)
ret i32 %spv.dot
}
>From f3dde287d84191e69ef5b7ee4f82a19171117605 Mon Sep 17 00:00:00 2001
From: Justin Bogner <m...@justinbogner.com>
Date: Sat, 17 May 2025 10:35:57 -0700
Subject: [PATCH 2/2] fixup: fix SM in tests
---
clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl | 7 ++++++-
clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl | 7 ++++++-
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
b/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
index fd9ded6a5d6bf..4a41f001b6618 100644
--- a/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
+++ b/clang/test/CodeGenHLSL/builtins/dot4add_i8packed.hlsl
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -finclude-default-header -triple
dxil-pc-shadermodel6.3-compute %s -emit-llvm -o - | FileCheck %s -DTARGET=dx
+// RUN: %clang_cc1 -finclude-default-header -triple
dxil-pc-shadermodel6.4-compute %s -emit-llvm -o - | FileCheck %s -DTARGET=dx
// RUN: %clang_cc1 -finclude-default-header -triple spirv-pc-vulkan-compute %s
-emit-llvm -o - | FileCheck %s -DTARGET=spv
// Test basic lowering to runtime function call.
@@ -17,3 +17,8 @@ int test(uint x, uint y, int acc) {
// CHECK: call i32 @llvm.[[TARGET]].dot4add.i8packed(i32 [[ACC0]], i32
[[X0]], i32 [[Y0]])
return dot4add_i8packed(x, y, acc);
}
+
+[numthreads(1,1,1)]
+void main() {
+ test(0, 0, 0);
+}
diff --git a/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
b/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
index 34f80a5ed1f57..e814da518d6bf 100644
--- a/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
+++ b/clang/test/CodeGenHLSL/builtins/dot4add_u8packed.hlsl
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -finclude-default-header -triple
dxil-pc-shadermodel6.3-compute %s -emit-llvm -o - | FileCheck %s -DTARGET=dx
+// RUN: %clang_cc1 -finclude-default-header -triple
dxil-pc-shadermodel6.4-compute %s -emit-llvm -o - | FileCheck %s -DTARGET=dx
// RUN: %clang_cc1 -finclude-default-header -triple spirv-pc-vulkan-compute %s
-emit-llvm -o - | FileCheck %s -DTARGET=spv
// Test basic lowering to runtime function call.
@@ -17,3 +17,8 @@ int test(uint x, uint y, int acc) {
// CHECK: call i32 @llvm.[[TARGET]].dot4add.u8packed(i32 [[ACC0]], i32
[[X0]], i32 [[Y0]])
return dot4add_u8packed(x, y, acc);
}
+
+[numthreads(1,1,1)]
+void main() {
+ test(0, 0, 0);
+}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
