[clang] Clang: Add minnum/maxnum builtin functions (PR #129207)
Matt Arsenault via cfe-commits
cfe-commits at lists.llvm.org
Fri Feb 28 00:37:42 PST 2025
================
@@ -0,0 +1,269 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
+// RUN: %clang_cc1 -disable-llvm-passes -O3 -triple x86_64 %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK
+
+typedef _Float16 half8 __attribute__((ext_vector_type(8)));
+typedef float float4 __attribute__((ext_vector_type(4)));
+typedef double double2 __attribute__((ext_vector_type(2)));
+typedef long double ldouble2 __attribute__((ext_vector_type(2)));
+
+// CHECK-LABEL: define dso_local half @fmin16(
+// CHECK-SAME: half noundef [[A:%.*]], half noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca half, align 2
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca half, align 2
+// CHECK-NEXT: store half [[A]], ptr [[A_ADDR]], align 2, !tbaa [[TBAA2:![0-9]+]]
+// CHECK-NEXT: store half [[B]], ptr [[B_ADDR]], align 2, !tbaa [[TBAA2]]
+// CHECK-NEXT: [[TMP0:%.*]] = load half, ptr [[A_ADDR]], align 2, !tbaa [[TBAA2]]
+// CHECK-NEXT: [[TMP1:%.*]] = load half, ptr [[B_ADDR]], align 2, !tbaa [[TBAA2]]
+// CHECK-NEXT: [[TMP2:%.*]] = call half @llvm.minnum.f16(half [[TMP0]], half [[TMP1]])
+// CHECK-NEXT: ret half [[TMP2]]
+//
+_Float16 fmin16(_Float16 a, _Float16 b) {
+ return __builtin_minnum(a, b);
+}
+// CHECK-LABEL: define dso_local <8 x half> @pfmin16(
+// CHECK-SAME: <8 x half> noundef [[A:%.*]], <8 x half> noundef [[B:%.*]]) #[[ATTR2:[0-9]+]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <8 x half>, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <8 x half>, align 16
+// CHECK-NEXT: store <8 x half> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA6:![0-9]+]]
+// CHECK-NEXT: store <8 x half> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP0:%.*]] = load <8 x half>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP1:%.*]] = load <8 x half>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MINNUM:%.*]] = call <8 x half> @llvm.minnum.v8f16(<8 x half> [[TMP0]], <8 x half> [[TMP1]])
+// CHECK-NEXT: ret <8 x half> [[ELT_MINNUM]]
+//
+half8 pfmin16(half8 a, half8 b) {
+ return __builtin_elementwise_minnum(a, b);
+}
+// CHECK-LABEL: define dso_local float @fmin32(
+// CHECK-SAME: float noundef [[A:%.*]], float noundef [[B:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca float, align 4
+// CHECK-NEXT: store float [[A]], ptr [[A_ADDR]], align 4, !tbaa [[TBAA7:![0-9]+]]
+// CHECK-NEXT: store float [[B]], ptr [[B_ADDR]], align 4, !tbaa [[TBAA7]]
+// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[A_ADDR]], align 4, !tbaa [[TBAA7]]
+// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[B_ADDR]], align 4, !tbaa [[TBAA7]]
+// CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.minnum.f32(float [[TMP0]], float [[TMP1]])
+// CHECK-NEXT: ret float [[TMP2]]
+//
+float fmin32(float a, float b) {
+ return __builtin_minnum(a, b);
+}
+// CHECK-LABEL: define dso_local <4 x float> @pfmin32(
+// CHECK-SAME: <4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) #[[ATTR2]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <4 x float>, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <4 x float>, align 16
+// CHECK-NEXT: store <4 x float> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <4 x float> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MINNUM:%.*]] = call <4 x float> @llvm.minnum.v4f32(<4 x float> [[TMP0]], <4 x float> [[TMP1]])
+// CHECK-NEXT: ret <4 x float> [[ELT_MINNUM]]
+//
+float4 pfmin32(float4 a, float4 b) {
+ return __builtin_elementwise_minnum(a, b);
+}
+// CHECK-LABEL: define dso_local double @fmin64(
+// CHECK-SAME: double noundef [[A:%.*]], double noundef [[B:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca double, align 8
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca double, align 8
+// CHECK-NEXT: store double [[A]], ptr [[A_ADDR]], align 8, !tbaa [[TBAA9:![0-9]+]]
+// CHECK-NEXT: store double [[B]], ptr [[B_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT: [[TMP0:%.*]] = load double, ptr [[A_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT: [[TMP1:%.*]] = load double, ptr [[B_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT: [[TMP2:%.*]] = call double @llvm.minnum.f64(double [[TMP0]], double [[TMP1]])
+// CHECK-NEXT: ret double [[TMP2]]
+//
+double fmin64(double a, double b) {
+ return __builtin_minnum(a, b);
+}
+// CHECK-LABEL: define dso_local <2 x double> @pfmin64(
+// CHECK-SAME: <2 x double> noundef [[A:%.*]], <2 x double> noundef [[B:%.*]]) #[[ATTR2]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x double>, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x double>, align 16
+// CHECK-NEXT: store <2 x double> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <2 x double> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP0:%.*]] = load <2 x double>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MINNUM:%.*]] = call <2 x double> @llvm.minnum.v2f64(<2 x double> [[TMP0]], <2 x double> [[TMP1]])
+// CHECK-NEXT: ret <2 x double> [[ELT_MINNUM]]
+//
+double2 pfmin64(double2 a, double2 b) {
+ return __builtin_elementwise_minnum(a, b);
+}
+
+// CHECK-LABEL: define dso_local x86_fp80 @fmin80(
+// CHECK-SAME: x86_fp80 noundef [[A:%.*]], x86_fp80 noundef [[B:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca x86_fp80, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca x86_fp80, align 16
+// CHECK-NEXT: store x86_fp80 [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA11:![0-9]+]]
+// CHECK-NEXT: store x86_fp80 [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA11]]
+// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, ptr [[A_ADDR]], align 16, !tbaa [[TBAA11]]
+// CHECK-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[B_ADDR]], align 16, !tbaa [[TBAA11]]
+// CHECK-NEXT: [[TMP2:%.*]] = call x86_fp80 @llvm.minnum.f80(x86_fp80 [[TMP0]], x86_fp80 [[TMP1]])
+// CHECK-NEXT: ret x86_fp80 [[TMP2]]
+//
+long double fmin80(long double a, long double b) {
+ return __builtin_minnum(a, b);
+}
+// CHECK-LABEL: define dso_local <2 x x86_fp80> @pfmin80(
+// CHECK-SAME: ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP0:%.*]], ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32
+// CHECK-NEXT: [[A:%.*]] = load <2 x x86_fp80>, ptr [[TMP0]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[B:%.*]] = load <2 x x86_fp80>, ptr [[TMP1]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <2 x x86_fp80> [[A]], ptr [[A_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <2 x x86_fp80> [[B]], ptr [[B_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP2:%.*]] = load <2 x x86_fp80>, ptr [[A_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP3:%.*]] = load <2 x x86_fp80>, ptr [[B_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MINNUM:%.*]] = call <2 x x86_fp80> @llvm.minnum.v2f80(<2 x x86_fp80> [[TMP2]], <2 x x86_fp80> [[TMP3]])
+// CHECK-NEXT: ret <2 x x86_fp80> [[ELT_MINNUM]]
+//
+ldouble2 pfmin80(ldouble2 a, ldouble2 b) {
+ return __builtin_elementwise_minnum(a, b);
+}
+
+// CHECK-LABEL: define dso_local half @fmax16(
+// CHECK-SAME: half noundef [[A:%.*]], half noundef [[B:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca half, align 2
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca half, align 2
+// CHECK-NEXT: store half [[A]], ptr [[A_ADDR]], align 2, !tbaa [[TBAA2]]
+// CHECK-NEXT: store half [[B]], ptr [[B_ADDR]], align 2, !tbaa [[TBAA2]]
+// CHECK-NEXT: [[TMP0:%.*]] = load half, ptr [[A_ADDR]], align 2, !tbaa [[TBAA2]]
+// CHECK-NEXT: [[TMP1:%.*]] = load half, ptr [[B_ADDR]], align 2, !tbaa [[TBAA2]]
+// CHECK-NEXT: [[TMP2:%.*]] = call half @llvm.maxnum.f16(half [[TMP0]], half [[TMP1]])
+// CHECK-NEXT: ret half [[TMP2]]
+//
+_Float16 fmax16(_Float16 a, _Float16 b) {
+ return __builtin_maxnum(a, b);
+}
+// CHECK-LABEL: define dso_local <8 x half> @pfmax16(
+// CHECK-SAME: <8 x half> noundef [[A:%.*]], <8 x half> noundef [[B:%.*]]) #[[ATTR2]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <8 x half>, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <8 x half>, align 16
+// CHECK-NEXT: store <8 x half> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <8 x half> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP0:%.*]] = load <8 x half>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP1:%.*]] = load <8 x half>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MAXNUM:%.*]] = call <8 x half> @llvm.maxnum.v8f16(<8 x half> [[TMP0]], <8 x half> [[TMP1]])
+// CHECK-NEXT: ret <8 x half> [[ELT_MAXNUM]]
+//
+half8 pfmax16(half8 a, half8 b) {
+ return __builtin_elementwise_maxnum(a, b);
+}
+// CHECK-LABEL: define dso_local float @fmax32(
+// CHECK-SAME: float noundef [[A:%.*]], float noundef [[B:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca float, align 4
+// CHECK-NEXT: store float [[A]], ptr [[A_ADDR]], align 4, !tbaa [[TBAA7]]
+// CHECK-NEXT: store float [[B]], ptr [[B_ADDR]], align 4, !tbaa [[TBAA7]]
+// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[A_ADDR]], align 4, !tbaa [[TBAA7]]
+// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[B_ADDR]], align 4, !tbaa [[TBAA7]]
+// CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.maxnum.f32(float [[TMP0]], float [[TMP1]])
+// CHECK-NEXT: ret float [[TMP2]]
+//
+float fmax32(float a, float b) {
+ return __builtin_maxnum(a, b);
+}
+// CHECK-LABEL: define dso_local <4 x float> @pfmax32(
+// CHECK-SAME: <4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) #[[ATTR2]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <4 x float>, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <4 x float>, align 16
+// CHECK-NEXT: store <4 x float> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <4 x float> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MAXNUM:%.*]] = call <4 x float> @llvm.maxnum.v4f32(<4 x float> [[TMP0]], <4 x float> [[TMP1]])
+// CHECK-NEXT: ret <4 x float> [[ELT_MAXNUM]]
+//
+float4 pfmax32(float4 a, float4 b) {
+ return __builtin_elementwise_maxnum(a, b);
+}
+// CHECK-LABEL: define dso_local double @fmax64(
+// CHECK-SAME: double noundef [[A:%.*]], double noundef [[B:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca double, align 8
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca double, align 8
+// CHECK-NEXT: store double [[A]], ptr [[A_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT: store double [[B]], ptr [[B_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT: [[TMP0:%.*]] = load double, ptr [[A_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT: [[TMP1:%.*]] = load double, ptr [[B_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT: [[TMP2:%.*]] = call double @llvm.maxnum.f64(double [[TMP0]], double [[TMP1]])
+// CHECK-NEXT: ret double [[TMP2]]
+//
+double fmax64(double a, double b) {
+ return __builtin_maxnum(a, b);
+}
+// CHECK-LABEL: define dso_local <2 x double> @pfmax64(
+// CHECK-SAME: <2 x double> noundef [[A:%.*]], <2 x double> noundef [[B:%.*]]) #[[ATTR2]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x double>, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x double>, align 16
+// CHECK-NEXT: store <2 x double> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <2 x double> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP0:%.*]] = load <2 x double>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MAXNUM:%.*]] = call <2 x double> @llvm.maxnum.v2f64(<2 x double> [[TMP0]], <2 x double> [[TMP1]])
+// CHECK-NEXT: ret <2 x double> [[ELT_MAXNUM]]
+//
+double2 pfmax64(double2 a, double2 b) {
+ return __builtin_elementwise_maxnum(a, b);
+}
+
+// CHECK-LABEL: define dso_local x86_fp80 @fmax80(
+// CHECK-SAME: x86_fp80 noundef [[A:%.*]], x86_fp80 noundef [[B:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca x86_fp80, align 16
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca x86_fp80, align 16
+// CHECK-NEXT: store x86_fp80 [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA11]]
+// CHECK-NEXT: store x86_fp80 [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA11]]
+// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, ptr [[A_ADDR]], align 16, !tbaa [[TBAA11]]
+// CHECK-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[B_ADDR]], align 16, !tbaa [[TBAA11]]
+// CHECK-NEXT: [[TMP2:%.*]] = call x86_fp80 @llvm.maxnum.f80(x86_fp80 [[TMP0]], x86_fp80 [[TMP1]])
+// CHECK-NEXT: ret x86_fp80 [[TMP2]]
+//
+long double fmax80(long double a, long double b) {
+ return __builtin_maxnum(a, b);
+}
+// CHECK-LABEL: define dso_local <2 x x86_fp80> @pfmax80(
+// CHECK-SAME: ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP0:%.*]], ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP1:%.*]]) #[[ATTR3]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32
+// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32
+// CHECK-NEXT: [[A:%.*]] = load <2 x x86_fp80>, ptr [[TMP0]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[B:%.*]] = load <2 x x86_fp80>, ptr [[TMP1]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <2 x x86_fp80> [[A]], ptr [[A_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: store <2 x x86_fp80> [[B]], ptr [[B_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP2:%.*]] = load <2 x x86_fp80>, ptr [[A_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[TMP3:%.*]] = load <2 x x86_fp80>, ptr [[B_ADDR]], align 32, !tbaa [[TBAA6]]
+// CHECK-NEXT: [[ELT_MINNUM:%.*]] = call <2 x x86_fp80> @llvm.minnum.v2f80(<2 x x86_fp80> [[TMP2]], <2 x x86_fp80> [[TMP3]])
+// CHECK-NEXT: ret <2 x x86_fp80> [[ELT_MINNUM]]
+//
+ldouble2 pfmax80(ldouble2 a, ldouble2 b) {
+ return __builtin_elementwise_minnum(a, b);
+}
+
----------------
arsenm wrote:
Missed the bfloat cases
https://github.com/llvm/llvm-project/pull/129207
More information about the cfe-commits
mailing list