[clang] [llvm] [IR] Don't set strictfp on irrelevant calls (PR #122735)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 13 08:09:25 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
@llvm/pr-subscribers-backend-amdgpu
Author: Serge Pavlov (spavloff)
<details>
<summary>Changes</summary>
RBuilder incorrectry assigned the attribute "strictfp" to any intrinsic function call in some cases inside strictfp functions. Accordinf to the documentation in https://llvm.org/docs/LangRef.html#function-attributes:
```
This attribute indicates that the function was called from a scope
that requires strict floating-point semantics. LLVM will not attempt
any optimizations that require assumptions about the floating-point
rounding mode or that might alter the state of floating-point status
flags that might otherwise be set or cleared by calling this
function.
```
Intrinsic functions like `llvm.fabs` do not depend on rounding mode, they also never raise any FP exception, so these restrictions make no sense for them. If a function interacts with FP environment, it must be either a constrained intrinsic or an external function.
---
Patch is 289.17 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/122735.diff
16 Files Affected:
- (modified) clang/test/CodeGen/SystemZ/strictfp_builtins.c (+9-9)
- (modified) clang/test/CodeGen/X86/strictfp_builtins.c (+3-3)
- (modified) clang/test/CodeGen/cx-complex-range.c (+10-10)
- (modified) clang/test/CodeGen/isfpclass.c (+9-9)
- (modified) clang/test/CodeGen/strictfp-elementwise-bulitins.cpp (+31-32)
- (modified) clang/test/CodeGen/strictfp_builtins.c (+10-10)
- (modified) clang/test/CodeGenOpenCL/cl20-device-side-enqueue-attributes.cl (+4-4)
- (modified) llvm/include/llvm/IR/IRBuilder.h (+2-14)
- (modified) llvm/include/llvm/IR/IntrinsicInst.h (+3)
- (modified) llvm/lib/IR/IRBuilder.cpp (+28)
- (modified) llvm/lib/IR/IntrinsicInst.cpp (+11)
- (modified) llvm/test/CodeGen/AMDGPU/amdgpu-simplify-libcall-pown.ll (+5-5)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomic_optimizer_fp_rtn.ll (+294-294)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_optimizer_fp_no_rtn.ll (+260-300)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll (+2-2)
- (modified) llvm/test/Transforms/HardwareLoops/scalar-while-strictfp.ll (+28-28)
``````````diff
diff --git a/clang/test/CodeGen/SystemZ/strictfp_builtins.c b/clang/test/CodeGen/SystemZ/strictfp_builtins.c
index 8c8f1f4cabd742..b60fd932d31c3f 100644
--- a/clang/test/CodeGen/SystemZ/strictfp_builtins.c
+++ b/clang/test/CodeGen/SystemZ/strictfp_builtins.c
@@ -9,7 +9,7 @@
// CHECK-NEXT: [[F_ADDR:%.*]] = alloca float, align 4
// CHECK-NEXT: store float [[F:%.*]], ptr [[F_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F_ADDR]], align 4
-// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f32(float [[TMP0]], i64 15) #[[ATTR2:[0-9]+]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f32(float [[TMP0]], i64 15)
// CHECK-NEXT: ret i32 [[TMP1]]
//
int test_isnan_float(float f) {
@@ -21,7 +21,7 @@ int test_isnan_float(float f) {
// CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8
// CHECK-NEXT: store double [[D:%.*]], ptr [[D_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load double, ptr [[D_ADDR]], align 8
-// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f64(double [[TMP0]], i64 15) #[[ATTR2]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f64(double [[TMP0]], i64 15)
// CHECK-NEXT: ret i32 [[TMP1]]
//
int test_isnan_double(double d) {
@@ -34,7 +34,7 @@ int test_isnan_double(double d) {
// CHECK-NEXT: [[LD:%.*]] = load fp128, ptr [[TMP0:%.*]], align 8
// CHECK-NEXT: store fp128 [[LD]], ptr [[LD_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load fp128, ptr [[LD_ADDR]], align 8
-// CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.s390.tdc.f128(fp128 [[TMP1]], i64 15) #[[ATTR2]]
+// CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.s390.tdc.f128(fp128 [[TMP1]], i64 15)
// CHECK-NEXT: ret i32 [[TMP2]]
//
int test_isnan_long_double(long double ld) {
@@ -46,7 +46,7 @@ int test_isnan_long_double(long double ld) {
// CHECK-NEXT: [[F_ADDR:%.*]] = alloca float, align 4
// CHECK-NEXT: store float [[F:%.*]], ptr [[F_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F_ADDR]], align 4
-// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f32(float [[TMP0]], i64 48) #[[ATTR2]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f32(float [[TMP0]], i64 48)
// CHECK-NEXT: ret i32 [[TMP1]]
//
int test_isinf_float(float f) {
@@ -58,7 +58,7 @@ int test_isinf_float(float f) {
// CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8
// CHECK-NEXT: store double [[D:%.*]], ptr [[D_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load double, ptr [[D_ADDR]], align 8
-// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f64(double [[TMP0]], i64 48) #[[ATTR2]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f64(double [[TMP0]], i64 48)
// CHECK-NEXT: ret i32 [[TMP1]]
//
int test_isinf_double(double d) {
@@ -71,7 +71,7 @@ int test_isinf_double(double d) {
// CHECK-NEXT: [[LD:%.*]] = load fp128, ptr [[TMP0:%.*]], align 8
// CHECK-NEXT: store fp128 [[LD]], ptr [[LD_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load fp128, ptr [[LD_ADDR]], align 8
-// CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.s390.tdc.f128(fp128 [[TMP1]], i64 48) #[[ATTR2]]
+// CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.s390.tdc.f128(fp128 [[TMP1]], i64 48)
// CHECK-NEXT: ret i32 [[TMP2]]
//
int test_isinf_long_double(long double ld) {
@@ -83,7 +83,7 @@ int test_isinf_long_double(long double ld) {
// CHECK-NEXT: [[F_ADDR:%.*]] = alloca float, align 4
// CHECK-NEXT: store float [[F:%.*]], ptr [[F_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[F_ADDR]], align 4
-// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f32(float [[TMP0]], i64 4032) #[[ATTR2]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f32(float [[TMP0]], i64 4032)
// CHECK-NEXT: ret i32 [[TMP1]]
//
int test_isfinite_float(float f) {
@@ -95,7 +95,7 @@ int test_isfinite_float(float f) {
// CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8
// CHECK-NEXT: store double [[D:%.*]], ptr [[D_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load double, ptr [[D_ADDR]], align 8
-// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f64(double [[TMP0]], i64 4032) #[[ATTR2]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.s390.tdc.f64(double [[TMP0]], i64 4032)
// CHECK-NEXT: ret i32 [[TMP1]]
//
int test_isfinite_double(double d) {
@@ -108,7 +108,7 @@ int test_isfinite_double(double d) {
// CHECK-NEXT: [[LD:%.*]] = load fp128, ptr [[TMP0:%.*]], align 8
// CHECK-NEXT: store fp128 [[LD]], ptr [[LD_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load fp128, ptr [[LD_ADDR]], align 8
-// CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.s390.tdc.f128(fp128 [[TMP1]], i64 4032) #[[ATTR2]]
+// CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.s390.tdc.f128(fp128 [[TMP1]], i64 4032)
// CHECK-NEXT: ret i32 [[TMP2]]
//
int test_isfinite_long_double(long double ld) {
diff --git a/clang/test/CodeGen/X86/strictfp_builtins.c b/clang/test/CodeGen/X86/strictfp_builtins.c
index 43e4060bef259b..c4a22dc5ee90fd 100644
--- a/clang/test/CodeGen/X86/strictfp_builtins.c
+++ b/clang/test/CodeGen/X86/strictfp_builtins.c
@@ -27,7 +27,7 @@ void p(char *str, int x) {
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16
// CHECK-NEXT: store x86_fp80 [[LD:%.*]], ptr [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, ptr [[LD_ADDR]], align 16
-// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f80(x86_fp80 [[TMP0]], i32 516) #[[ATTR3]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f80(x86_fp80 [[TMP0]], i32 516)
// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32
// CHECK-NEXT: call void @p(ptr noundef @.str.1, i32 noundef [[TMP2]]) #[[ATTR3]]
// CHECK-NEXT: ret void
@@ -43,7 +43,7 @@ void test_long_double_isinf(long double ld) {
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16
// CHECK-NEXT: store x86_fp80 [[LD:%.*]], ptr [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, ptr [[LD_ADDR]], align 16
-// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f80(x86_fp80 [[TMP0]], i32 504) #[[ATTR3]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f80(x86_fp80 [[TMP0]], i32 504)
// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32
// CHECK-NEXT: call void @p(ptr noundef @.str.2, i32 noundef [[TMP2]]) #[[ATTR3]]
// CHECK-NEXT: ret void
@@ -59,7 +59,7 @@ void test_long_double_isfinite(long double ld) {
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16
// CHECK-NEXT: store x86_fp80 [[LD:%.*]], ptr [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, ptr [[LD_ADDR]], align 16
-// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f80(x86_fp80 [[TMP0]], i32 3) #[[ATTR3]]
+// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f80(x86_fp80 [[TMP0]], i32 3)
// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32
// CHECK-NEXT: call void @p(ptr noundef @.str.3, i32 noundef [[TMP2]]) #[[ATTR3]]
// CHECK-NEXT: ret void
diff --git a/clang/test/CodeGen/cx-complex-range.c b/clang/test/CodeGen/cx-complex-range.c
index 88300041061aae..98735c4671ce52 100644
--- a/clang/test/CodeGen/cx-complex-range.c
+++ b/clang/test/CodeGen/cx-complex-range.c
@@ -1575,8 +1575,8 @@ _Complex float mulf(_Complex float a, _Complex float b) {
// X86WINPRMTD_STRICT-NEXT: [[B_REAL:%.*]] = load double, ptr [[B_REALP]], align 8
// X86WINPRMTD_STRICT-NEXT: [[B_IMAGP:%.*]] = getelementptr inbounds nuw { double, double }, ptr [[B]], i32 0, i32 1
// X86WINPRMTD_STRICT-NEXT: [[B_IMAG:%.*]] = load double, ptr [[B_IMAGP]], align 8
-// X86WINPRMTD_STRICT-NEXT: [[TMP0:%.*]] = call double @llvm.fabs.f64(double [[B_REAL]]) #[[ATTR3]]
-// X86WINPRMTD_STRICT-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[B_IMAG]]) #[[ATTR3]]
+// X86WINPRMTD_STRICT-NEXT: [[TMP0:%.*]] = call double @llvm.fabs.f64(double [[B_REAL]])
+// X86WINPRMTD_STRICT-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[B_IMAG]])
// X86WINPRMTD_STRICT-NEXT: [[ABS_CMP:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double [[TMP1]], metadata !"ugt", metadata !"fpexcept.strict") #[[ATTR3]]
// X86WINPRMTD_STRICT-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]]
// X86WINPRMTD_STRICT: abs_rhsr_greater_or_equal_abs_rhsi:
@@ -2658,8 +2658,8 @@ _Complex double muld(_Complex double a, _Complex double b) {
// X86WINPRMTD_STRICT-NEXT: [[B_REAL:%.*]] = load double, ptr [[B_REALP]], align 8
// X86WINPRMTD_STRICT-NEXT: [[B_IMAGP:%.*]] = getelementptr inbounds nuw { double, double }, ptr [[B]], i32 0, i32 1
// X86WINPRMTD_STRICT-NEXT: [[B_IMAG:%.*]] = load double, ptr [[B_IMAGP]], align 8
-// X86WINPRMTD_STRICT-NEXT: [[TMP0:%.*]] = call double @llvm.fabs.f64(double [[B_REAL]]) #[[ATTR3]]
-// X86WINPRMTD_STRICT-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[B_IMAG]]) #[[ATTR3]]
+// X86WINPRMTD_STRICT-NEXT: [[TMP0:%.*]] = call double @llvm.fabs.f64(double [[B_REAL]])
+// X86WINPRMTD_STRICT-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[B_IMAG]])
// X86WINPRMTD_STRICT-NEXT: [[ABS_CMP:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double [[TMP1]], metadata !"ugt", metadata !"fpexcept.strict") #[[ATTR3]]
// X86WINPRMTD_STRICT-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]]
// X86WINPRMTD_STRICT: abs_rhsr_greater_or_equal_abs_rhsi:
@@ -2713,8 +2713,8 @@ _Complex double muld(_Complex double a, _Complex double b) {
// PRMTD_STRICT-NEXT: [[B_REAL:%.*]] = load x86_fp80, ptr [[B_REALP]], align 16
// PRMTD_STRICT-NEXT: [[B_IMAGP:%.*]] = getelementptr inbounds nuw { x86_fp80, x86_fp80 }, ptr [[B]], i32 0, i32 1
// PRMTD_STRICT-NEXT: [[B_IMAG:%.*]] = load x86_fp80, ptr [[B_IMAGP]], align 16
-// PRMTD_STRICT-NEXT: [[TMP0:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[B_REAL]]) #[[ATTR4]]
-// PRMTD_STRICT-NEXT: [[TMP1:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[B_IMAG]]) #[[ATTR4]]
+// PRMTD_STRICT-NEXT: [[TMP0:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[B_REAL]])
+// PRMTD_STRICT-NEXT: [[TMP1:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[B_IMAG]])
// PRMTD_STRICT-NEXT: [[ABS_CMP:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f80(x86_fp80 [[TMP0]], x86_fp80 [[TMP1]], metadata !"ugt", metadata !"fpexcept.strict") #[[ATTR4]]
// PRMTD_STRICT-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]]
// PRMTD_STRICT: abs_rhsr_greater_or_equal_abs_rhsi:
@@ -3961,8 +3961,8 @@ _Complex long double mulld(_Complex long double a, _Complex long double b) {
// X86WINPRMTD_STRICT-NEXT: [[C_IMAG:%.*]] = load float, ptr [[C_IMAGP]], align 4
// X86WINPRMTD_STRICT-NEXT: [[CONV:%.*]] = call double @llvm.experimental.constrained.fpext.f64.f32(float [[C_REAL]], metadata !"fpexcept.strict") #[[ATTR3]]
// X86WINPRMTD_STRICT-NEXT: [[CONV1:%.*]] = call double @llvm.experimental.constrained.fpext.f64.f32(float [[C_IMAG]], metadata !"fpexcept.strict") #[[ATTR3]]
-// X86WINPRMTD_STRICT-NEXT: [[TMP0:%.*]] = call double @llvm.fabs.f64(double [[CONV]]) #[[ATTR3]]
-// X86WINPRMTD_STRICT-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[CONV1]]) #[[ATTR3]]
+// X86WINPRMTD_STRICT-NEXT: [[TMP0:%.*]] = call double @llvm.fabs.f64(double [[CONV]])
+// X86WINPRMTD_STRICT-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[CONV1]])
// X86WINPRMTD_STRICT-NEXT: [[ABS_CMP:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double [[TMP1]], metadata !"ugt", metadata !"fpexcept.strict") #[[ATTR3]]
// X86WINPRMTD_STRICT-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]]
// X86WINPRMTD_STRICT: abs_rhsr_greater_or_equal_abs_rhsi:
@@ -4038,8 +4038,8 @@ _Complex long double mulld(_Complex long double a, _Complex long double b) {
// PRMTD_STRICT-NEXT: [[C_IMAG:%.*]] = load float, ptr [[C_IMAGP]], align 4
// PRMTD_STRICT-NEXT: [[CONV:%.*]] = call x86_fp80 @llvm.experimental.constrained.fpext.f80.f32(float [[C_REAL]], metadata !"fpexcept.strict") #[[ATTR4]]
// PRMTD_STRICT-NEXT: [[CONV1:%.*]] = call x86_fp80 @llvm.experimental.constrained.fpext.f80.f32(float [[C_IMAG]], metadata !"fpexcept.strict") #[[ATTR4]]
-// PRMTD_STRICT-NEXT: [[TMP0:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[CONV]]) #[[ATTR4]]
-// PRMTD_STRICT-NEXT: [[TMP1:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[CONV1]]) #[[ATTR4]]
+// PRMTD_STRICT-NEXT: [[TMP0:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[CONV]])
+// PRMTD_STRICT-NEXT: [[TMP1:%.*]] = call x86_fp80 @llvm.fabs.f80(x86_fp80 [[CONV1]])
// PRMTD_STRICT-NEXT: [[ABS_CMP:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f80(x86_fp80 [[TMP0]], x86_fp80 [[TMP1]], metadata !"ugt", metadata !"fpexcept.strict") #[[ATTR4]]
// PRMTD_STRICT-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]]
// PRMTD_STRICT: abs_rhsr_greater_or_equal_abs_rhsi:
diff --git a/clang/test/CodeGen/isfpclass.c b/clang/test/CodeGen/isfpclass.c
index 1bf60b8fbca176..58849eec340c67 100644
--- a/clang/test/CodeGen/isfpclass.c
+++ b/clang/test/CodeGen/isfpclass.c
@@ -15,7 +15,7 @@ _Bool check_isfpclass_finite(float x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isfpclass_finite_strict
// CHECK-SAME: (float noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 504) #[[ATTR5:[0-9]+]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 504)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isfpclass_finite_strict(float x) {
@@ -36,7 +36,7 @@ _Bool check_isfpclass_nan_f32(float x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isfpclass_nan_f32_strict
// CHECK-SAME: (float noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 3) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 3)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isfpclass_nan_f32_strict(float x) {
@@ -57,7 +57,7 @@ _Bool check_isfpclass_snan_f64(double x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isfpclass_snan_f64_strict
// CHECK-SAME: (double noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f64(double [[X]], i32 1) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f64(double [[X]], i32 1)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isfpclass_snan_f64_strict(double x) {
@@ -78,7 +78,7 @@ _Bool check_isfpclass_zero_f16(_Float16 x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isfpclass_zero_f16_strict
// CHECK-SAME: (half noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f16(half [[X]], i32 96) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f16(half [[X]], i32 96)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isfpclass_zero_f16_strict(_Float16 x) {
@@ -89,7 +89,7 @@ _Bool check_isfpclass_zero_f16_strict(_Float16 x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isnan
// CHECK-SAME: (float noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 3) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 3)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isnan(float x) {
@@ -100,7 +100,7 @@ _Bool check_isnan(float x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isinf
// CHECK-SAME: (float noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 516) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 516)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isinf(float x) {
@@ -111,7 +111,7 @@ _Bool check_isinf(float x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isfinite
// CHECK-SAME: (float noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 504) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 504)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isfinite(float x) {
@@ -122,7 +122,7 @@ _Bool check_isfinite(float x) {
// CHECK-LABEL: define dso_local noundef i1 @check_isnormal
// CHECK-SAME: (float noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 264) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[X]], i32 264)
// CHECK-NEXT: ret i1 [[TMP0]]
//
_Bool check_isnormal(float x) {
@@ -150,7 +150,7 @@ int4 check_isfpclass_nan_v4f32(float4 x) {
// CHECK-LABEL: define dso_local range(i32 0, 2) <4 x i32> @check_isfpclass_nan_strict_v4f32
// CHECK-SAME: (<4 x float> noundef [[X:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[TMP0:%.*]] = tail call <4 x i1> @llvm.is.fpclass.v4f32(<4 x float> [[X]], i32 3) #[[ATTR5]]
+// CHECK-NEXT: [[TMP0:%.*]] = tail call <4 x i1> @llvm.is.fpclass.v4f32(<4 x float> [[X]], i32 3)
// CHECK-NEXT: [[TMP1:%.*]] = zext <4 x i1> [[TMP0]] to <4 x i32>
// CHECK-NEXT: ret <4 x i32> [[TMP1]]
//
diff --git a/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp b/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp
index 175ad22601839d..9ba1a557a90fee 100644
--- a/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp
+++ b/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp
@@ -20,7 +20,7 @@ float4 strict_fadd(float4 a, float4 b) {
// CHECK-LABEL: define dso_local noundef <4 x float> @_Z22strict_elementwise_absDv4_f
// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) local_unnamed_addr #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[ELT_ABS:%.*]] = tail call <4 x float> @llvm.fabs.v4f32(<4 x float> [[A]]) #[[ATTR4]]
+// CHECK-NEXT: [[ELT_ABS:%.*]] = tail call <4 x float> @llvm.fabs.v4f32(<4 x float> [[A]])
// CHECK-NEXT: ret <4 x float> [[ELT_ABS]]
//
float4 strict_elementwise_abs(float4 a) {
@@ -50,7 +50,7 @@ float4 strict_elementwise_min(float4 a, float4 b) {
// CHECK-LABEL: define dso_local noundef <4 x float> @_Z26strict_elementwise_maximumDv4_fS_
// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[ELT_MAXIMUM:%.*]] = tail call <4 x float> @llvm.maximum.v4f32(<4 x float> [[A]], <4 x float> [[B]]) #[[ATTR4]]
+// CHECK-NEXT: [[ELT_MAXIMUM:%.*]] = tail call <4 x float> @llvm.maximum.v4f32(<4 x float> [[A]], <4 x float> [[B]])
// CHECK-NEXT: ret <4 x float> [[ELT_MAXIMUM]]
//
float4 strict_elementwise_maximum(float4 a, float4 b) {
@@ -60,7 +60,7 @@ float4 strict_elementwise_maximum(float4 a, float4 b) {
// CHECK-LABEL: define dso_local noundef <4 x float> @_Z26strict_elementwise_minimumDv4_fS_
// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[ELT_MINIMUM:%.*]] = tail call <4 x float> @llvm.minimum.v4f32(<4 x float> [[A]], <4 x float> [[B]]) #[[ATTR4]]
+// CHECK-NEXT: [[ELT_MINIMUM:%.*]] = tail call <4 x float> @llvm.minimum.v4f32(<4 x float> [[A]], <4 x float> [[B]])
// CHECK-NEXT: ret <4 x float> [[ELT_MINIMUM]]
//
float4 strict_elementwise_minimum(float4 a, float4 b) {
@@ -70,7 +70,7 @@ float4 strict_elementwise_minimum(float4 a, float4 b) {
// CHECK-LABEL: define dso_local noundef <4 x float> @_Z23strict_elementwise_ceilDv4_f
// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
-// CHECK-NEXT:...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/122735
More information about the llvm-commits
mailing list