effective-light updated this revision to Diff 339048.
effective-light added a comment.
Use the correct clang command.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D100834/new/
https://reviews.llvm.org/D100834
Files:
clang/lib/CodeGen/CGExprScalar.cpp
clang/test/CodeGen/fp-matrix-pragma.c
Index: clang/test/CodeGen/fp-matrix-pragma.c
===================================================================
--- /dev/null
+++ clang/test/CodeGen/fp-matrix-pragma.c
@@ -0,0 +1,33 @@
+// RUN: %clang -emit-llvm -S -fenable-matrix -mllvm -disable-llvm-optzns %s -o
- | FileCheck %s
+
+typedef float fx2x2_t __attribute__((matrix_type(2, 2)));
+typedef int ix2x2_t __attribute__((matrix_type(2, 2)));
+
+fx2x2_t fp_matrix_contract(fx2x2_t a, fx2x2_t b, float c, float d) {
+// CHECK: call contract <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32
+// CHECK: fdiv contract <4 x float>
+// CHECK: fmul contract <4 x float>
+#pragma clang fp contract(fast)
+ return (a * b / c) * d;
+}
+
+fx2x2_t fp_matrix_reassoc(fx2x2_t a, fx2x2_t b, fx2x2_t c) {
+// CHECK: fadd reassoc <4 x float>
+// CHECK: fsub reassoc <4 x float>
+#pragma clang fp reassociate(on)
+ return a + b - c;
+}
+
+fx2x2_t fp_matrix_ops(fx2x2_t a, fx2x2_t b, fx2x2_t c) {
+// CHECK: call reassoc contract <4 x float>
@llvm.matrix.multiply.v4f32.v4f32.v4f32
+// CHECK: fadd reassoc contract <4 x float>
+#pragma clang fp contract(fast) reassociate(on)
+ return a * b + c;
+}
+
+ix2x2_t int_matrix_ops(ix2x2_t a, ix2x2_t b, ix2x2_t c) {
+// CHECK: call <4 x i32> @llvm.matrix.multiply.v4i32.v4i32.v4i32
+// CHECK: add <4 x i32>
+#pragma clang fp contract(fast) reassociate(on)
+ return a * b + c;
+}
Index: clang/lib/CodeGen/CGExprScalar.cpp
===================================================================
--- clang/lib/CodeGen/CGExprScalar.cpp
+++ clang/lib/CodeGen/CGExprScalar.cpp
@@ -732,6 +732,7 @@
BO->getLHS()->getType().getCanonicalType());
auto *RHSMatTy = dyn_cast<ConstantMatrixType>(
BO->getRHS()->getType().getCanonicalType());
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
if (LHSMatTy && RHSMatTy)
return MB.CreateMatrixMultiply(Ops.LHS, Ops.RHS,
LHSMatTy->getNumRows(),
LHSMatTy->getNumColumns(),
@@ -3206,6 +3207,7 @@
"first operand must be a matrix");
assert(BO->getRHS()->getType().getCanonicalType()->isArithmeticType() &&
"second operand must be an arithmetic type");
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
return MB.CreateScalarDiv(Ops.LHS, Ops.RHS,
Ops.Ty->hasUnsignedIntegerRepresentation());
}
@@ -3585,6 +3587,7 @@
if (op.Ty->isConstantMatrixType()) {
llvm::MatrixBuilder<CGBuilderTy> MB(Builder);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
return MB.CreateAdd(op.LHS, op.RHS);
}
@@ -3734,6 +3737,7 @@
if (op.Ty->isConstantMatrixType()) {
llvm::MatrixBuilder<CGBuilderTy> MB(Builder);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
return MB.CreateSub(op.LHS, op.RHS);
}
Index: clang/test/CodeGen/fp-matrix-pragma.c
===================================================================
--- /dev/null
+++ clang/test/CodeGen/fp-matrix-pragma.c
@@ -0,0 +1,33 @@
+// RUN: %clang -emit-llvm -S -fenable-matrix -mllvm -disable-llvm-optzns %s -o - | FileCheck %s
+
+typedef float fx2x2_t __attribute__((matrix_type(2, 2)));
+typedef int ix2x2_t __attribute__((matrix_type(2, 2)));
+
+fx2x2_t fp_matrix_contract(fx2x2_t a, fx2x2_t b, float c, float d) {
+// CHECK: call contract <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32
+// CHECK: fdiv contract <4 x float>
+// CHECK: fmul contract <4 x float>
+#pragma clang fp contract(fast)
+ return (a * b / c) * d;
+}
+
+fx2x2_t fp_matrix_reassoc(fx2x2_t a, fx2x2_t b, fx2x2_t c) {
+// CHECK: fadd reassoc <4 x float>
+// CHECK: fsub reassoc <4 x float>
+#pragma clang fp reassociate(on)
+ return a + b - c;
+}
+
+fx2x2_t fp_matrix_ops(fx2x2_t a, fx2x2_t b, fx2x2_t c) {
+// CHECK: call reassoc contract <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32
+// CHECK: fadd reassoc contract <4 x float>
+#pragma clang fp contract(fast) reassociate(on)
+ return a * b + c;
+}
+
+ix2x2_t int_matrix_ops(ix2x2_t a, ix2x2_t b, ix2x2_t c) {
+// CHECK: call <4 x i32> @llvm.matrix.multiply.v4i32.v4i32.v4i32
+// CHECK: add <4 x i32>
+#pragma clang fp contract(fast) reassociate(on)
+ return a * b + c;
+}
Index: clang/lib/CodeGen/CGExprScalar.cpp
===================================================================
--- clang/lib/CodeGen/CGExprScalar.cpp
+++ clang/lib/CodeGen/CGExprScalar.cpp
@@ -732,6 +732,7 @@
BO->getLHS()->getType().getCanonicalType());
auto *RHSMatTy = dyn_cast<ConstantMatrixType>(
BO->getRHS()->getType().getCanonicalType());
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
if (LHSMatTy && RHSMatTy)
return MB.CreateMatrixMultiply(Ops.LHS, Ops.RHS, LHSMatTy->getNumRows(),
LHSMatTy->getNumColumns(),
@@ -3206,6 +3207,7 @@
"first operand must be a matrix");
assert(BO->getRHS()->getType().getCanonicalType()->isArithmeticType() &&
"second operand must be an arithmetic type");
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
return MB.CreateScalarDiv(Ops.LHS, Ops.RHS,
Ops.Ty->hasUnsignedIntegerRepresentation());
}
@@ -3585,6 +3587,7 @@
if (op.Ty->isConstantMatrixType()) {
llvm::MatrixBuilder<CGBuilderTy> MB(Builder);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
return MB.CreateAdd(op.LHS, op.RHS);
}
@@ -3734,6 +3737,7 @@
if (op.Ty->isConstantMatrixType()) {
llvm::MatrixBuilder<CGBuilderTy> MB(Builder);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
return MB.CreateSub(op.LHS, op.RHS);
}
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
