[llvm] [TLI][NFC] Autogenerate vectorized libcall tests for SLEEF/ArmPL. (PR #76146)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Dec 21 04:58:58 PST 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Alexandros Lamprineas (labrinea)
<details>
<summary>Changes</summary>
This patch prepares the ground for #<!-- -->76060.
* Replaces deprecated float* and double* types with ptr
* Adds `noalias` attribute to pointer arguments
* Adds some cmd-line options to the RUN lines for simplified output
* Removes datalayout since target triple is provided
* Removes checks for return statements
* Makes the pattern-matching for autogenerated checks more explicit
* Removes redundant test file suffix (already under the AArch64 dir)
---
Patch is 141.35 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/76146.diff
2 Files Affected:
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/armpl-calls.ll (+579-364)
- (renamed) llvm/test/Transforms/LoopVectorize/AArch64/sleef-calls.ll (+309-421)
``````````diff
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/armpl-calls.ll b/llvm/test/Transforms/LoopVectorize/AArch64/armpl-calls.ll
index aa5fdf59e14c02..ea8581cc862d1c 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/armpl-calls.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/armpl-calls.ll
@@ -1,21 +1,23 @@
-; RUN: opt -vector-library=ArmPL -passes=inject-tli-mappings,loop-vectorize -S < %s | FileCheck %s --check-prefixes=CHECK,NEON
-; RUN: opt -mattr=+sve -vector-library=ArmPL -passes=inject-tli-mappings,loop-vectorize -S < %s | FileCheck %s --check-prefixes=CHECK,SVE
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter "call.*(cos|sin|tan|cbrt|erf|^exp|gamma|log|sqrt|copysign|dim|min|mod|hypot|nextafter|pow|fma|mod)" --version 4
+; RUN: opt -vector-library=ArmPL -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=ArmPL -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"
-
; Tests are checking if LV can vectorize loops with function calls
; using mappings from TLI for scalable and fixed width vectorization.
declare double @acos(double)
declare float @acosf(float)
-define void @acos_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @acos_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vacosq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svacos_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @acos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @acos_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vacosq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @acos_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svacos_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -35,11 +37,14 @@ define void @acos_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @acos_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @acos_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vacosq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svacos_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @acos_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @acos_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vacosq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @acos_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svacos_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -62,11 +67,14 @@ define void @acos_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @acosh(double)
declare float @acoshf(float)
-define void @acosh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @acosh_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vacoshq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svacosh_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @acosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @acosh_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vacoshq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @acosh_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svacosh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -86,11 +94,14 @@ define void @acosh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @acosh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @acosh_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vacoshq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svacosh_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @acosh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @acosh_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vacoshq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @acosh_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svacosh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -113,11 +124,14 @@ define void @acosh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @asin(double)
declare float @asinf(float)
-define void @asin_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @asin_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vasinq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svasin_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @asin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @asin_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vasinq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @asin_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svasin_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -137,11 +151,14 @@ define void @asin_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @asin_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @asin_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vasinq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svasin_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @asin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @asin_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vasinq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @asin_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svasin_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -164,11 +181,14 @@ define void @asin_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @asinh(double)
declare float @asinhf(float)
-define void @asinh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @asinh_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vasinhq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svasinh_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @asinh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @asinh_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vasinhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @asinh_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svasinh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -188,11 +208,14 @@ define void @asinh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @asinh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @asinh_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vasinhq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svasinh_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @asinh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @asinh_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vasinhq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @asinh_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svasinh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -215,11 +238,14 @@ define void @asinh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @atan(double)
declare float @atanf(float)
-define void @atan_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @atan_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vatanq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svatan_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @atan_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @atan_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vatanq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @atan_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svatan_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -239,11 +265,14 @@ define void @atan_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @atan_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @atan_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vatanq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svatan_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @atan_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @atan_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vatanq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @atan_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svatan_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -266,11 +295,14 @@ define void @atan_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @atanh(double)
declare float @atanhf(float)
-define void @atanh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @atanh_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vatanhq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svatanh_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @atanh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @atanh_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vatanhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @atanh_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svatanh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -290,11 +322,14 @@ define void @atanh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @atanh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @atanh_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vatanhq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svatanh_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @atanh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @atanh_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vatanhq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @atanh_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svatanh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -317,11 +352,14 @@ define void @atanh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @cbrt(double)
declare float @cbrtf(float)
-define void @cbrt_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @cbrt_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vcbrtq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svcbrt_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @cbrt_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @cbrt_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vcbrtq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @cbrt_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcbrt_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -341,11 +379,14 @@ define void @cbrt_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @cbrt_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @cbrt_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vcbrtq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svcbrt_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @cbrt_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @cbrt_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vcbrtq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @cbrt_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcbrt_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -368,11 +409,14 @@ define void @cbrt_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @cos(double)
declare float @cosf(float)
-define void @cos_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @cos_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vcosq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svcos_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @cos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @cos_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vcosq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @cos_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcos_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -392,11 +436,14 @@ define void @cos_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @cos_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @cos_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vcosq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svcos_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @cos_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @cos_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vcosq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @cos_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcos_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -419,11 +466,14 @@ define void @cos_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @cosh(double)
declare float @coshf(float)
-define void @cosh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @cosh_f64(
-; NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vcoshq_f64(<2 x double> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 2 x double> @armpl_svcosh_f64_x(<vscale x 2 x double> [[TMP4:%.*]], <vscale x 2 x i1> {{.*}})
-; CHECK: ret void
+define void @cosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @cosh_f64(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vcoshq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @cosh_f64(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcosh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -443,11 +493,14 @@ define void @cosh_f64(ptr nocapture %in.ptr, ptr %out.ptr) {
ret void
}
-define void @cosh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
-; CHECK-LABEL: @cosh_f32(
-; NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vcoshq_f32(<4 x float> [[TMP4:%.*]])
-; SVE: [[TMP5:%.*]] = call <vscale x 4 x float> @armpl_svcosh_f32_x(<vscale x 4 x float> [[TMP4:%.*]], <vscale x 4 x i1> {{.*}})
-; CHECK: ret void
+define void @cosh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
+; NEON-LABEL: define void @cosh_f32(
+; NEON-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) {
+; NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vcoshq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+;
+; SVE-LABEL: define void @cosh_f32(
+; SVE-SAME: ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SVE: [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcosh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
entry:
br label %for.body
@@ -470,11 +523,14 @@ define void @cosh_f32(ptr nocapture %in.ptr, ptr %out.ptr) {
declare double @erf(double)
declare float @erff...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/76146
More information about the llvm-commits
mailing list