[llvm] [LV] Use requested calling convention for vector math routines (PR #136122)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Apr 17 03:43:30 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: David Sherwood (david-arm)
<details>
<summary>Changes</summary>
Some vector math routines, e.g. ArmPL, specify a particular
calling convention on the routines which can help improve
performance by specifying what registers have to be preserved
across the call.
---
Patch is 337.87 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/136122.diff
3 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp (+2)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll (+480-480)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/veclib-intrinsic-calls.ll (+232-232)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index 2cc558f49ccce..733cb4990c859 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -1231,6 +1231,8 @@ void VPWidenCallRecipe::execute(VPTransformState &State) {
CallInst *V = State.Builder.CreateCall(Variant, Args, OpBundles);
setFlags(V);
+ if (CallingConv::ID ID = Variant->getCallingConv())
+ V->setCallingConv(ID);
if (!V->getType()->isVoidTy())
State.set(this, V);
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll b/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
index 4ad9987b09069..c6ea44bb85f11 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
@@ -21,28 +21,28 @@ declare float @acosf(float)
define void @acos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; SLEEF-NEON-LABEL: define void @acos_f64
; SLEEF-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
-; SLEEF-NEON: [[TMP3:%.*]] = call <2 x double> @_ZGVnN2v_acos(<2 x double> [[WIDE_LOAD:%.*]])
+; SLEEF-NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_acos(<2 x double> [[WIDE_LOAD:%.*]])
;
; SLEEF-SVE-LABEL: define void @acos_f64
; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
-; SLEEF-SVE: [[TMP13:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @acos_f64
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
-; SLEEF-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
+; SLEEF-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
; SLEEF-SVE-NOPRED: [[CALL:%.*]] = tail call double @acos(double [[IN:%.*]])
;
; ARMPL-NEON-LABEL: define void @acos_f64
; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
-; ARMPL-NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vacosq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+; ARMPL-NEON: [[TMP2:%.*]] = call aarch64_vector_pcs <2 x double> @armpl_vacosq_f64(<2 x double> [[WIDE_LOAD:%.*]])
;
; ARMPL-SVE-LABEL: define void @acos_f64
; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
-; ARMPL-SVE: [[TMP13:%.*]] = 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:%.*]])
+; ARMPL-SVE: [[TMP12:%.*]] = 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:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @acos_f64
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
-; ARMPL-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svacos_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
+; ARMPL-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 2 x double> @armpl_svacos_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
; ARMPL-SVE-NOPRED: [[CALL:%.*]] = tail call double @acos(double [[IN:%.*]])
;
entry:
@@ -66,28 +66,28 @@ define void @acos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
define void @acos_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; SLEEF-NEON-LABEL: define void @acos_f32
; SLEEF-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP3:%.*]] = call <4 x float> @_ZGVnN4v_acosf(<4 x float> [[WIDE_LOAD:%.*]])
+; SLEEF-NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_acosf(<4 x float> [[WIDE_LOAD:%.*]])
;
; SLEEF-SVE-LABEL: define void @acos_f32
; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[TMP13:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @acos_f32
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
+; SLEEF-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
; SLEEF-SVE-NOPRED: [[CALL:%.*]] = tail call float @acosf(float [[IN:%.*]])
;
; ARMPL-NEON-LABEL: define void @acos_f32
; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vacosq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+; ARMPL-NEON: [[TMP2:%.*]] = call aarch64_vector_pcs <4 x float> @armpl_vacosq_f32(<4 x float> [[WIDE_LOAD:%.*]])
;
; ARMPL-SVE-LABEL: define void @acos_f32
; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP13:%.*]] = 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:%.*]])
+; ARMPL-SVE: [[TMP12:%.*]] = 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:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @acos_f32
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svacos_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
+; ARMPL-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 4 x float> @armpl_svacos_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
; ARMPL-SVE-NOPRED: [[CALL:%.*]] = tail call float @acosf(float [[IN:%.*]])
;
entry:
@@ -114,28 +114,28 @@ declare float @acoshf(float)
define void @acosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; SLEEF-NEON-LABEL: define void @acosh_f64
; SLEEF-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP3:%.*]] = call <2 x double> @_ZGVnN2v_acosh(<2 x double> [[WIDE_LOAD:%.*]])
+; SLEEF-NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_acosh(<2 x double> [[WIDE_LOAD:%.*]])
;
; SLEEF-SVE-LABEL: define void @acosh_f64
; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[TMP13:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acosh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acosh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @acosh_f64
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acosh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
+; SLEEF-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acosh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
; SLEEF-SVE-NOPRED: [[CALL:%.*]] = tail call double @acosh(double [[IN:%.*]])
;
; ARMPL-NEON-LABEL: define void @acosh_f64
; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vacoshq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+; ARMPL-NEON: [[TMP2:%.*]] = call aarch64_vector_pcs <2 x double> @armpl_vacoshq_f64(<2 x double> [[WIDE_LOAD:%.*]])
;
; ARMPL-SVE-LABEL: define void @acosh_f64
; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP13:%.*]] = 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:%.*]])
+; ARMPL-SVE: [[TMP12:%.*]] = 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:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @acosh_f64
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svacosh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
+; ARMPL-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 2 x double> @armpl_svacosh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
; ARMPL-SVE-NOPRED: [[CALL:%.*]] = tail call double @acosh(double [[IN:%.*]])
;
entry:
@@ -159,28 +159,28 @@ define void @acosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
define void @acosh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; SLEEF-NEON-LABEL: define void @acosh_f32
; SLEEF-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP3:%.*]] = call <4 x float> @_ZGVnN4v_acoshf(<4 x float> [[WIDE_LOAD:%.*]])
+; SLEEF-NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_acoshf(<4 x float> [[WIDE_LOAD:%.*]])
;
; SLEEF-SVE-LABEL: define void @acosh_f32
; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[TMP13:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acoshf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acoshf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @acosh_f32
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acoshf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
+; SLEEF-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acoshf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
; SLEEF-SVE-NOPRED: [[CALL:%.*]] = tail call float @acoshf(float [[IN:%.*]])
;
; ARMPL-NEON-LABEL: define void @acosh_f32
; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vacoshq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+; ARMPL-NEON: [[TMP2:%.*]] = call aarch64_vector_pcs <4 x float> @armpl_vacoshq_f32(<4 x float> [[WIDE_LOAD:%.*]])
;
; ARMPL-SVE-LABEL: define void @acosh_f32
; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP13:%.*]] = 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:%.*]])
+; ARMPL-SVE: [[TMP12:%.*]] = 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:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @acosh_f32
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svacosh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
+; ARMPL-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 4 x float> @armpl_svacosh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
; ARMPL-SVE-NOPRED: [[CALL:%.*]] = tail call float @acoshf(float [[IN:%.*]])
;
entry:
@@ -207,28 +207,28 @@ declare float @asinf(float)
define void @asin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; SLEEF-NEON-LABEL: define void @asin_f64
; SLEEF-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP3:%.*]] = call <2 x double> @_ZGVnN2v_asin(<2 x double> [[WIDE_LOAD:%.*]])
+; SLEEF-NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_asin(<2 x double> [[WIDE_LOAD:%.*]])
;
; SLEEF-SVE-LABEL: define void @asin_f64
; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[TMP13:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @asin_f64
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
+; SLEEF-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
; SLEEF-SVE-NOPRED: [[CALL:%.*]] = tail call double @asin(double [[IN:%.*]])
;
; ARMPL-NEON-LABEL: define void @asin_f64
; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vasinq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+; ARMPL-NEON: [[TMP2:%.*]] = call aarch64_vector_pcs <2 x double> @armpl_vasinq_f64(<2 x double> [[WIDE_LOAD:%.*]])
;
; ARMPL-SVE-LABEL: define void @asin_f64
; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP13:%.*]] = 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:%.*]])
+; ARMPL-SVE: [[TMP12:%.*]] = 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:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @asin_f64
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svasin_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
+; ARMPL-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 2 x double> @armpl_svasin_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
; ARMPL-SVE-NOPRED: [[CALL:%.*]] = tail call double @asin(double [[IN:%.*]])
;
entry:
@@ -252,28 +252,28 @@ define void @asin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
define void @asin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; SLEEF-NEON-LABEL: define void @asin_f32
; SLEEF-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP3:%.*]] = call <4 x float> @_ZGVnN4v_asinf(<4 x float> [[WIDE_LOAD:%.*]])
+; SLEEF-NEON: [[TMP2:%.*]] = call <4 x float> @_ZGVnN4v_asinf(<4 x float> [[WIDE_LOAD:%.*]])
;
; SLEEF-SVE-LABEL: define void @asin_f32
; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[TMP13:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE: [[TMP12:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @asin_f32
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
+; SLEEF-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
; SLEEF-SVE-NOPRED: [[CALL:%.*]] = tail call float @asinf(float [[IN:%.*]])
;
; ARMPL-NEON-LABEL: define void @asin_f32
; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP3:%.*]] = call <4 x float> @armpl_vasinq_f32(<4 x float> [[WIDE_LOAD:%.*]])
+; ARMPL-NEON: [[TMP2:%.*]] = call aarch64_vector_pcs <4 x float> @armpl_vasinq_f32(<4 x float> [[WIDE_LOAD:%.*]])
;
; ARMPL-SVE-LABEL: define void @asin_f32
; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP13:%.*]] = 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:%.*]])
+; ARMPL-SVE: [[TMP12:%.*]] = 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:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @asin_f32
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svasin_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
+; ARMPL-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 4 x float> @armpl_svasin_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> splat (i1 true))
; ARMPL-SVE-NOPRED: [[CALL:%.*]] = tail call float @asinf(float [[IN:%.*]])
;
entry:
@@ -300,28 +300,28 @@ declare float @asinhf(float)
define void @asinh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; SLEEF-NEON-LABEL: define void @asinh_f64
; SLEEF-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP3:%.*]] = call <2 x double> @_ZGVnN2v_asinh(<2 x double> [[WIDE_LOAD:%.*]])
+; SLEEF-NEON: [[TMP2:%.*]] = call <2 x double> @_ZGVnN2v_asinh(<2 x double> [[WIDE_LOAD:%.*]])
;
; SLEEF-SVE-LABEL: define void @asinh_f64
; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[TMP13:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asinh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asinh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @asinh_f64
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asinh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
+; SLEEF-SVE-NOPRED: [[TMP8:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asinh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> splat (i1 true))
; SLEEF-SVE-NOPRED: [[CALL:%.*]] = tail call double @asinh(double [[IN:%.*]])
;
; ARMPL-NEON-LABEL: define void @asinh_f64
; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP3:%.*]] = call <2 x double> @armpl_vasinhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
+; ARMPL-NEON: [[TMP2:%.*]] = call aarch64_vector_pcs <2 x double> @armpl_vasinhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
;
; ARMPL-SVE-LABEL: define void @asinh_f64
; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP13:%.*]] = 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:%.*]])
+; ARMPL-SVE: [[TMP12:%.*]] = call <vscale x 2 x double> @armpl_svasinh_f64_x(<vscale x 2 x dou...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/136122
More information about the llvm-commits
mailing list