[llvm] [TLI][AArch64] Remove VecFuncs mapping for functions with output pointers (PR #108967)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 17 05:18:52 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-analysis
@llvm/pr-subscribers-llvm-transforms
Author: Benjamin Maxwell (MacDue)
<details>
<summary>Changes</summary>
This removes the ArmPL and SLEEF (GNU ABI) mappings for sincos, sincospi and modf. This is due to the issue that LoopAccessAnalysis currently does not check/track aliasing from the output pointers, but assumes vectorizing library calls with a mapping is safe.
This can result in incorrect codegen if something like the following is vectorized:
```
for(int i=0; i<N; i++) {
// No aliasing between input and output pointers detected.
sincos(cos_out[0], sin_out+i, cos_out+i);
}
```
Where for VF >= 2 `cos_out[1]` to `cos_out[VF-1]` is the cosine of the original value of `cos_out[0]` not the updated value.
---
Patch is 34.48 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/108967.diff
3 Files Affected:
- (modified) llvm/include/llvm/Analysis/VecFuncs.def (-36)
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll (+45-48)
- (modified) llvm/test/Transforms/Util/add-TLI-mappings.ll (+3-147)
``````````diff
diff --git a/llvm/include/llvm/Analysis/VecFuncs.def b/llvm/include/llvm/Analysis/VecFuncs.def
index 532a3ca334b1ae..472760f9cb2bc5 100644
--- a/llvm/include/llvm/Analysis/VecFuncs.def
+++ b/llvm/include/llvm/Analysis/VecFuncs.def
@@ -590,8 +590,6 @@ TLI_DEFINE_VECFUNC("log1p", "_ZGVnN2v_log1p", FIXED(2), "_ZGV_LLVM_N2v")
TLI_DEFINE_VECFUNC("log2", "_ZGVnN2v_log2", FIXED(2), "_ZGV_LLVM_N2v")
TLI_DEFINE_VECFUNC("llvm.log2.f64", "_ZGVnN2v_log2", FIXED(2), "_ZGV_LLVM_N2v")
-TLI_DEFINE_VECFUNC("modf", "_ZGVnN2vl8_modf", FIXED(2), "_ZGV_LLVM_N2vl8")
-
TLI_DEFINE_VECFUNC("nextafter", "_ZGVnN2vv_nextafter", FIXED(2), "_ZGV_LLVM_N2vv")
TLI_DEFINE_VECFUNC("pow", "_ZGVnN2vv_pow", FIXED(2), "_ZGV_LLVM_N2vv")
@@ -600,10 +598,6 @@ TLI_DEFINE_VECFUNC("llvm.pow.f64", "_ZGVnN2vv_pow", FIXED(2), "_ZGV_LLVM_N2vv")
TLI_DEFINE_VECFUNC("sin", "_ZGVnN2v_sin", FIXED(2), "_ZGV_LLVM_N2v")
TLI_DEFINE_VECFUNC("llvm.sin.f64", "_ZGVnN2v_sin", FIXED(2), "_ZGV_LLVM_N2v")
-TLI_DEFINE_VECFUNC("sincos", "_ZGVnN2vl8l8_sincos", FIXED(2), "_ZGV_LLVM_N2vl8l8")
-
-TLI_DEFINE_VECFUNC("sincospi", "_ZGVnN2vl8l8_sincospi", FIXED(2), "_ZGV_LLVM_N2vl8l8")
-
TLI_DEFINE_VECFUNC("sinh", "_ZGVnN2v_sinh", FIXED(2), "_ZGV_LLVM_N2v")
TLI_DEFINE_VECFUNC("llvm.sinh.f64", "_ZGVnN2v_sinh", FIXED(2), "_ZGV_LLVM_N2v")
@@ -694,8 +688,6 @@ TLI_DEFINE_VECFUNC("log1pf", "_ZGVnN4v_log1pf", FIXED(4), "_ZGV_LLVM_N4v")
TLI_DEFINE_VECFUNC("log2f", "_ZGVnN4v_log2f", FIXED(4), "_ZGV_LLVM_N4v")
TLI_DEFINE_VECFUNC("llvm.log2.f32", "_ZGVnN4v_log2f", FIXED(4), "_ZGV_LLVM_N4v")
-TLI_DEFINE_VECFUNC("modff", "_ZGVnN4vl4_modff", FIXED(4), "_ZGV_LLVM_N4vl4")
-
TLI_DEFINE_VECFUNC("nextafterf", "_ZGVnN4vv_nextafterf", FIXED(4), "_ZGV_LLVM_N4vv")
TLI_DEFINE_VECFUNC("powf", "_ZGVnN4vv_powf", FIXED(4), "_ZGV_LLVM_N4vv")
@@ -704,10 +696,6 @@ TLI_DEFINE_VECFUNC("llvm.pow.f32", "_ZGVnN4vv_powf", FIXED(4), "_ZGV_LLVM_N4vv")
TLI_DEFINE_VECFUNC("sinf", "_ZGVnN4v_sinf", FIXED(4), "_ZGV_LLVM_N4v")
TLI_DEFINE_VECFUNC("llvm.sin.f32", "_ZGVnN4v_sinf", FIXED(4), "_ZGV_LLVM_N4v")
-TLI_DEFINE_VECFUNC("sincosf", "_ZGVnN4vl4l4_sincosf", FIXED(4), "_ZGV_LLVM_N4vl4l4")
-
-TLI_DEFINE_VECFUNC("sincospif", "_ZGVnN4vl4l4_sincospif", FIXED(4), "_ZGV_LLVM_N4vl4l4")
-
TLI_DEFINE_VECFUNC("sinhf", "_ZGVnN4v_sinhf", FIXED(4), "_ZGV_LLVM_N4v")
TLI_DEFINE_VECFUNC("llvm.sinh.f32", "_ZGVnN4v_sinhf", FIXED(4), "_ZGV_LLVM_N4v")
@@ -840,9 +828,6 @@ TLI_DEFINE_VECFUNC("log2f", "_ZGVsMxv_log2f", SCALABLE(4), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("llvm.log2.f64", "_ZGVsMxv_log2", SCALABLE(2), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("llvm.log2.f32", "_ZGVsMxv_log2f", SCALABLE(4), MASKED, "_ZGVsMxv")
-TLI_DEFINE_VECFUNC("modf", "_ZGVsNxvl8_modf", SCALABLE(2), NOMASK, "_ZGVsNxvl8")
-TLI_DEFINE_VECFUNC("modff", "_ZGVsNxvl4_modff", SCALABLE(4), NOMASK, "_ZGVsNxvl4")
-
TLI_DEFINE_VECFUNC("nextafter", "_ZGVsMxvv_nextafter", SCALABLE(2), MASKED, "_ZGVsMxvv")
TLI_DEFINE_VECFUNC("nextafterf", "_ZGVsMxvv_nextafterf", SCALABLE(4), MASKED, "_ZGVsMxvv")
@@ -856,12 +841,6 @@ TLI_DEFINE_VECFUNC("sinf", "_ZGVsMxv_sinf", SCALABLE(4), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("llvm.sin.f64", "_ZGVsMxv_sin", SCALABLE(2), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("llvm.sin.f32", "_ZGVsMxv_sinf", SCALABLE(4), MASKED, "_ZGVsMxv")
-TLI_DEFINE_VECFUNC("sincos", "_ZGVsNxvl8l8_sincos", SCALABLE(2), NOMASK, "_ZGVsNxvl8l8")
-TLI_DEFINE_VECFUNC("sincosf", "_ZGVsNxvl4l4_sincosf", SCALABLE(4), NOMASK, "_ZGVsNxvl4l4")
-
-TLI_DEFINE_VECFUNC("sincospi", "_ZGVsNxvl8l8_sincospi", SCALABLE(2), NOMASK, "_ZGVsNxvl8l8")
-TLI_DEFINE_VECFUNC("sincospif", "_ZGVsNxvl4l4_sincospif", SCALABLE(4), NOMASK, "_ZGVsNxvl4l4")
-
TLI_DEFINE_VECFUNC("sinh", "_ZGVsMxv_sinh", SCALABLE(2), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("sinhf", "_ZGVsMxv_sinhf", SCALABLE(4), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("llvm.sinh.f64", "_ZGVsMxv_sinh", SCALABLE(2), MASKED, "_ZGVsMxv")
@@ -1098,11 +1077,6 @@ TLI_DEFINE_VECFUNC("llvm.log2.f32", "armpl_vlog2q_f32", FIXED(4), NOMASK, "_ZGV_
TLI_DEFINE_VECFUNC("llvm.log2.f64", "armpl_svlog2_f64_x", SCALABLE(2), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("llvm.log2.f32", "armpl_svlog2_f32_x", SCALABLE(4), MASKED, "_ZGVsMxv")
-TLI_DEFINE_VECFUNC("modf", "armpl_vmodfq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vl8")
-TLI_DEFINE_VECFUNC("modff", "armpl_vmodfq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vl4")
-TLI_DEFINE_VECFUNC("modf", "armpl_svmodf_f64_x", SCALABLE(2), MASKED, "_ZGVsMxvl8")
-TLI_DEFINE_VECFUNC("modff", "armpl_svmodf_f32_x", SCALABLE(4), MASKED, "_ZGVsMxvl4")
-
TLI_DEFINE_VECFUNC("nextafter", "armpl_vnextafterq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vv")
TLI_DEFINE_VECFUNC("nextafterf", "armpl_vnextafterq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vv")
TLI_DEFINE_VECFUNC("nextafter", "armpl_svnextafter_f64_x", SCALABLE(2), MASKED, "_ZGVsMxvv")
@@ -1128,16 +1102,6 @@ TLI_DEFINE_VECFUNC("llvm.sin.f32", "armpl_vsinq_f32", FIXED(4), NOMASK, "_ZGV_LL
TLI_DEFINE_VECFUNC("llvm.sin.f64", "armpl_svsin_f64_x", SCALABLE(2), MASKED, "_ZGVsMxv")
TLI_DEFINE_VECFUNC("llvm.sin.f32", "armpl_svsin_f32_x", SCALABLE(4), MASKED, "_ZGVsMxv")
-TLI_DEFINE_VECFUNC("sincos", "armpl_vsincosq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vl8l8")
-TLI_DEFINE_VECFUNC("sincosf", "armpl_vsincosq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vl4l4")
-TLI_DEFINE_VECFUNC("sincos", "armpl_svsincos_f64_x", SCALABLE(2), MASKED, "_ZGVsMxvl8l8")
-TLI_DEFINE_VECFUNC("sincosf", "armpl_svsincos_f32_x", SCALABLE(4), MASKED, "_ZGVsMxvl4l4")
-
-TLI_DEFINE_VECFUNC("sincospi", "armpl_vsincospiq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vl8l8")
-TLI_DEFINE_VECFUNC("sincospif", "armpl_vsincospiq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vl4l4")
-TLI_DEFINE_VECFUNC("sincospi", "armpl_svsincospi_f64_x", SCALABLE(2), MASKED, "_ZGVsMxvl8l8")
-TLI_DEFINE_VECFUNC("sincospif", "armpl_svsincospi_f32_x", SCALABLE(4), MASKED, "_ZGVsMxvl4l4")
-
TLI_DEFINE_VECFUNC("sinh", "armpl_vsinhq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2v")
TLI_DEFINE_VECFUNC("sinhf", "armpl_vsinhq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4v")
TLI_DEFINE_VECFUNC("sinh", "armpl_svsinh_f64_x", SCALABLE(2), MASKED, "_ZGVsMxv")
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll b/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
index d9cc630482fc80..41ccb3c404dd76 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
@@ -2902,35 +2902,36 @@ define void @log2_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
ret void
}
+; FIXME: Re-enable modf[f] vectorization once aliasing issues due to output
+; pointers have been resolved.
+
declare double @modf(double, ptr)
declare float @modff(float, ptr)
define void @modf_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; SLEEF-NEON-LABEL: define void @modf_f64
; SLEEF-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP5:%.*]] = call <2 x double> @_ZGVnN2vl8_modf(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP4:%.*]])
+; SLEEF-NEON: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; SLEEF-SVE-LABEL: define void @modf_f64
; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR4:[0-9]+]]
+; SLEEF-SVE: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @modf_f64
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP17:%.*]] = call <vscale x 2 x double> @_ZGVsNxvl8_modf(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP16:%.*]])
-; SLEEF-SVE-NOPRED: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR64:[0-9]+]]
+; SLEEF-SVE-NOPRED: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; ARMPL-NEON-LABEL: define void @modf_f64
; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP5:%.*]] = call <2 x double> @armpl_vmodfq_f64(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP4:%.*]])
+; ARMPL-NEON: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; ARMPL-SVE-LABEL: define void @modf_f64
; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP23:%.*]] = call <vscale x 2 x double> @armpl_svmodf_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP22:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @modf_f64
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: [[TMP17:%.*]] = call <vscale x 2 x double> @armpl_svmodf_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP16:%.*]], <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))
-; ARMPL-SVE-NOPRED: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR64:[0-9]+]]
+; ARMPL-SVE-NOPRED: [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]])
;
entry:
br label %for.body
@@ -2954,29 +2955,27 @@ for.cond.cleanup:
define void @modf_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; SLEEF-NEON-LABEL: define void @modf_f32
; SLEEF-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: [[TMP5:%.*]] = call <4 x float> @_ZGVnN4vl4_modff(<4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP4:%.*]])
+; SLEEF-NEON: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; SLEEF-SVE-LABEL: define void @modf_f32
; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR5:[0-9]+]]
+; SLEEF-SVE: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @modf_f32
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: [[TMP17:%.*]] = call <vscale x 4 x float> @_ZGVsNxvl4_modff(<vscale x 4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP16:%.*]])
-; SLEEF-SVE-NOPRED: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR65:[0-9]+]]
+; SLEEF-SVE-NOPRED: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; ARMPL-NEON-LABEL: define void @modf_f32
; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: [[TMP5:%.*]] = call <4 x float> @armpl_vmodfq_f32(<4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP4:%.*]])
+; ARMPL-NEON: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; ARMPL-SVE-LABEL: define void @modf_f32
; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: [[TMP23:%.*]] = call <vscale x 4 x float> @armpl_svmodf_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP22:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @modf_f32
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: [[TMP17:%.*]] = call <vscale x 4 x float> @armpl_svmodf_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP16:%.*]], <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))
-; ARMPL-SVE-NOPRED: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR65:[0-9]+]]
+; ARMPL-SVE-NOPRED: [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]])
;
entry:
br label %for.body
@@ -3276,35 +3275,36 @@ define void @sin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
ret void
}
+; FIXME: Re-enable sincos[f] vectorization once aliasing issues with output
+; pointers have been resolved.
+
declare void @sincos(double, ptr, ptr)
declare void @sincosf(float, ptr, ptr)
define void @sincos_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; SLEEF-NEON-LABEL: define void @sincos_f64
; SLEEF-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: call void @_ZGVnN2vl8l8_sincos(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
+; SLEEF-NEON: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; SLEEF-SVE-LABEL: define void @sincos_f64
; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR6:[0-9]+]]
+; SLEEF-SVE: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @sincos_f64
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: call void @_ZGVsNxvl8l8_sincos(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]])
-; SLEEF-SVE-NOPRED: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR72:[0-9]+]]
+; SLEEF-SVE-NOPRED: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-NEON-LABEL: define void @sincos_f64
; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: call void @armpl_vsincosq_f64(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
+; ARMPL-NEON: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-SVE-LABEL: define void @sincos_f64
; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: call void @armpl_svsincos_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @sincos_f64
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: call void @armpl_svsincos_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]], <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))
-; ARMPL-SVE-NOPRED: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR72:[0-9]+]]
+; ARMPL-SVE-NOPRED: call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
entry:
br label %for.body
@@ -3327,29 +3327,27 @@ for.cond.cleanup:
define void @sincos_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; SLEEF-NEON-LABEL: define void @sincos_f32
; SLEEF-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: call void @_ZGVnN4vl4l4_sincosf(<4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
+; SLEEF-NEON: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; SLEEF-SVE-LABEL: define void @sincos_f32
; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR7:[0-9]+]]
+; SLEEF-SVE: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @sincos_f32
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: call void @_ZGVsNxvl4l4_sincosf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]])
-; SLEEF-SVE-NOPRED: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR73:[0-9]+]]
+; SLEEF-SVE-NOPRED: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-NEON-LABEL: define void @sincos_f32
; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: call void @armpl_vsincosq_f32(<4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
+; ARMPL-NEON: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-SVE-LABEL: define void @sincos_f32
; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: call void @armpl_svsincos_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-SVE-NOPRED-LABEL: define void @sincos_f32
; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE-NOPRED: call void @armpl_svsincos_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]], <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))
-; ARMPL-SVE-NOPRED: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR73:[0-9]+]]
+; ARMPL-SVE-NOPRED: call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
entry:
br label %for.body
@@ -3369,35 +3367,36 @@ for.cond.cleanup:
ret void
}
+; FIXME: Re-enable sincospi[f] vectorization once aliasing issues with output
+; pointers have been resolved.
+
declare void @sincospi(double, ptr, ptr)
declare void @sincospif(float, ptr, ptr)
define void @sincospi_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
; SLEEF-NEON-LABEL: define void @sincospi_f64
; SLEEF-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-NEON: call void @_ZGVnN2vl8l8_sincospi(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
+; SLEEF-NEON: call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; SLEEF-SVE-LABEL: define void @sincospi_f64
; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE: call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR8:[0-9]+]]
+; SLEEF-SVE: call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; SLEEF-SVE-NOPRED-LABEL: define void @sincospi_f64
; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE-NOPRED: call void @_ZGVsNxvl8l8_sincospi(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]])
-; SLEEF-SVE-NOPRED: call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR74:[0-9]+]]
+; SLEEF-SVE-NOPRED: call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-NEON-LABEL: define void @sincospi_f64
; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-NEON: call void @armpl_vsincospiq_f64(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
+; ARMPL-NEON: call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]])
;
; ARMPL-SVE-LABEL: define void @sincospi_f64
; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE: call void @armpl_svsincospi_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/108967
More information about the llvm-commits
mailing list