[llvm] [TLI] Add SLEEF mappings for fmod/fmodf fixed-width. (PR #75803)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Dec 18 06:48:15 PST 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Paschalis Mpeis (paschalis-mpeis)
<details>
<summary>Changes</summary>
Cleanup test sleef-calls-aarch64.ll:
- make the util update script's regex more clear
- eliminate scalar epilogues in tests
---
Patch is 46.92 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/75803.diff
2 Files Affected:
- (modified) llvm/include/llvm/Analysis/VecFuncs.def (+2)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/sleef-calls-aarch64.ll (+49-142)
``````````diff
diff --git a/llvm/include/llvm/Analysis/VecFuncs.def b/llvm/include/llvm/Analysis/VecFuncs.def
index c628e72b24d12b..4bffcdee6f9caa 100644
--- a/llvm/include/llvm/Analysis/VecFuncs.def
+++ b/llvm/include/llvm/Analysis/VecFuncs.def
@@ -493,6 +493,7 @@ TLI_DEFINE_VECFUNC( "llvm.exp2.f64", "_ZGVnN2v_exp2", FIXED(2), "_ZGV_LLVM_N2v")
TLI_DEFINE_VECFUNC( "exp10", "_ZGVnN2v_exp10", FIXED(2), "_ZGV_LLVM_N2v")
TLI_DEFINE_VECFUNC( "llvm.exp10.f64", "_ZGVnN2v_exp10", FIXED(2), "_ZGV_LLVM_N2v")
+TLI_DEFINE_VECFUNC("fmod", "_ZGVnN2vv_fmod", FIXED(2), "_ZGV_LLVM_N2vv")
TLI_DEFINE_VECFUNC( "lgamma", "_ZGVnN2v_lgamma", FIXED(2), "_ZGV_LLVM_N2v")
@@ -546,6 +547,7 @@ TLI_DEFINE_VECFUNC( "llvm.exp2.f32", "_ZGVnN4v_exp2f", FIXED(4), "_ZGV_LLVM_N4v"
TLI_DEFINE_VECFUNC( "exp10f", "_ZGVnN4v_exp10f", FIXED(4), "_ZGV_LLVM_N4v")
TLI_DEFINE_VECFUNC( "llvm.exp10.f32", "_ZGVnN4v_exp10f", FIXED(4), "_ZGV_LLVM_N4v")
+TLI_DEFINE_VECFUNC("fmodf", "_ZGVnN4vv_fmodf", FIXED(4), "_ZGV_LLVM_N4vv")
TLI_DEFINE_VECFUNC( "lgammaf", "_ZGVnN4v_lgammaf", FIXED(4), "_ZGV_LLVM_N4v")
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sleef-calls-aarch64.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sleef-calls-aarch64.ll
index d7dc122edaf7e2..bd39dcb3371a92 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sleef-calls-aarch64.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sleef-calls-aarch64.ll
@@ -1,8 +1,7 @@
-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter "(_)|(cos|exp[^e]|fmod|gamma|log|pow|sin|sqrt|tan)|(ret)" --version 2
-; RUN: opt -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefix=NEON
-; RUN: opt -mattr=+sve -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefix=SVE
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter "(_)|(cos|expf?\(|exp2|exp10|fmod|gamma|log|pow|sin|sqrt|tan)|(ret)" --version 2
+; RUN: opt -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize,simplifycfg -prefer-predicate-over-epilogue=predicate-dont-vectorize -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefix=NEON
+; RUN: opt -mattr=+sve -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize,simplifycfg -prefer-predicate-over-epilogue=predicate-dont-vectorize -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefix=SVE
-target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-unknown-linux-gnu"
declare double @acos(double)
@@ -12,13 +11,11 @@ define void @acos_f64(double* nocapture %varray) {
; NEON-LABEL: define void @acos_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_acos(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @acos(double [[CONV:%.*]]) #[[ATTR0:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @acos_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0:[0-9]+]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @acos(double [[CONV:%.*]]) #[[ATTR2:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -43,13 +40,11 @@ define void @acos_f32(float* nocapture %varray) {
; NEON-LABEL: define void @acos_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_acosf(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @acosf(float [[CONV:%.*]]) #[[ATTR1:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @acos_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @acosf(float [[CONV:%.*]]) #[[ATTR3:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -77,13 +72,11 @@ define void @asin_f64(double* nocapture %varray) {
; NEON-LABEL: define void @asin_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_asin(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @asin(double [[CONV:%.*]]) #[[ATTR2:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @asin_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @asin(double [[CONV:%.*]]) #[[ATTR4:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -108,13 +101,11 @@ define void @asin_f32(float* nocapture %varray) {
; NEON-LABEL: define void @asin_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_asinf(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @asinf(float [[CONV:%.*]]) #[[ATTR3:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @asin_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @asinf(float [[CONV:%.*]]) #[[ATTR5:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -142,13 +133,11 @@ define void @atan_f64(double* nocapture %varray) {
; NEON-LABEL: define void @atan_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_atan(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @atan(double [[CONV:%.*]]) #[[ATTR4:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @atan_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atan(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @atan(double [[CONV:%.*]]) #[[ATTR6:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atan(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -173,13 +162,11 @@ define void @atan_f32(float* nocapture %varray) {
; NEON-LABEL: define void @atan_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_atanf(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @atanf(float [[CONV:%.*]]) #[[ATTR5:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @atan_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanf(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @atanf(float [[CONV:%.*]]) #[[ATTR7:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanf(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -207,13 +194,11 @@ define void @atan2_f64(double* nocapture %varray) {
; NEON-LABEL: define void @atan2_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2vv_atan2(<2 x double> [[TMP1:%.*]], <2 x double> [[TMP1]])
-; NEON: [[CALL:%.*]] = tail call double @atan2(double [[CONV:%.*]], double [[CONV]]) #[[ATTR6:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @atan2_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_atan2(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x double> [[TMP11]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @atan2(double [[CONV:%.*]], double [[CONV]]) #[[ATTR8:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_atan2(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x double> [[TMP19]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -238,13 +223,11 @@ define void @atan2_f32(float* nocapture %varray) {
; NEON-LABEL: define void @atan2_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4vv_atan2f(<4 x float> [[TMP1:%.*]], <4 x float> [[TMP1]])
-; NEON: [[CALL:%.*]] = tail call float @atan2f(float [[CONV:%.*]], float [[CONV]]) #[[ATTR7:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @atan2_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_atan2f(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x float> [[TMP11]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @atan2f(float [[CONV:%.*]], float [[CONV]]) #[[ATTR9:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_atan2f(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x float> [[TMP19]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -272,13 +255,11 @@ define void @atanh_f64(double* nocapture %varray) {
; NEON-LABEL: define void @atanh_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_atanh(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @atanh(double [[CONV:%.*]]) #[[ATTR8:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @atanh_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atanh(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @atanh(double [[CONV:%.*]]) #[[ATTR10:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atanh(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -303,13 +284,11 @@ define void @atanh_f32(float* nocapture %varray) {
; NEON-LABEL: define void @atanh_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_atanhf(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @atanhf(float [[CONV:%.*]]) #[[ATTR9:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @atanh_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanhf(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @atanhf(float [[CONV:%.*]]) #[[ATTR11:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanhf(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -337,13 +316,11 @@ define void @cos_f64(double* nocapture %varray) {
; NEON-LABEL: define void @cos_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_cos(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @cos(double [[CONV:%.*]]) #[[ATTR10:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @cos_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cos(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @cos(double [[CONV:%.*]]) #[[ATTR12:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cos(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -368,13 +345,11 @@ define void @cos_f32(float* nocapture %varray) {
; NEON-LABEL: define void @cos_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_cosf(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @cosf(float [[CONV:%.*]]) #[[ATTR11:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @cos_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cosf(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @cosf(float [[CONV:%.*]]) #[[ATTR13:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cosf(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -402,13 +377,11 @@ define void @cosh_f64(double* nocapture %varray) {
; NEON-LABEL: define void @cosh_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_cosh(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @cosh(double [[CONV:%.*]]) #[[ATTR12:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @cosh_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cosh(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @cosh(double [[CONV:%.*]]) #[[ATTR14:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cosh(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -433,13 +406,11 @@ define void @cosh_f32(float* nocapture %varray) {
; NEON-LABEL: define void @cosh_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_coshf(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @coshf(float [[CONV:%.*]]) #[[ATTR13:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @cosh_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_coshf(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @coshf(float [[CONV:%.*]]) #[[ATTR15:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_coshf(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -467,13 +438,11 @@ define void @exp_f64(double* nocapture %varray) {
; NEON-LABEL: define void @exp_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_exp(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @exp(double [[CONV:%.*]]) #[[ATTR14:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @exp_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @exp(double [[CONV:%.*]]) #[[ATTR16:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -498,13 +467,11 @@ define void @exp_f32(float* nocapture %varray) {
; NEON-LABEL: define void @exp_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_expf(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @expf(float [[CONV:%.*]]) #[[ATTR15:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @exp_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_expf(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call float @expf(float [[CONV:%.*]]) #[[ATTR17:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_expf(<vscale x 4 x float> [[TMP19:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -532,13 +499,11 @@ define void @exp2_f64(double* nocapture %varray) {
; NEON-LABEL: define void @exp2_f64
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_exp2(<2 x double> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call double @exp2(double [[CONV:%.*]]) #[[ATTR16:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @exp2_f64
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp2(<vscale x 2 x double> [[TMP11:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SVE: [[CALL:%.*]] = tail call double @exp2(double [[CONV:%.*]]) #[[ATTR18:[0-9]+]]
+; SVE: [[TMP20:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp2(<vscale x 2 x double> [[TMP19:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
; SVE: ret void
;
entry:
@@ -563,13 +528,11 @@ define void @exp2_f32(float* nocapture %varray) {
; NEON-LABEL: define void @exp2_f32
; NEON-SAME: (ptr nocapture [[VARRAY:%.*]]) {
; NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_exp2f(<4 x float> [[TMP1:%.*]])
-; NEON: [[CALL:%.*]] = tail call float @exp2f(float [[CONV:%.*]]) #[[ATTR17:[0-9]+]]
; NEON: ret void
;
; SVE-LABEL: define void @exp2_f32
; SVE-SAME: (ptr nocapture [[VARRAY:%.*]]) #[[ATTR0]] {
-; SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_exp2f(<vscale x 4 x float> [[TMP11:%.*]], <vscale x 4 x i1> shufflevector (<vscale...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/75803
More information about the llvm-commits
mailing list