b16e694948
If the cost of original scalar instruction + cast is better than the extractelement from the vector cast instruction, better to keep original scalar instructions, where possible Reviewers: RKSimon Reviewed By: RKSimon Pull Request: https://github.com/llvm/llvm-project/pull/110537
45 lines
1.9 KiB
LLVM
45 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: %if x86-registered-target %{ opt -S --passes=slp-vectorizer -slp-threshold=-10 < %s -mtriple=x86_64-pc-windows-msvc19.39.33523 | FileCheck %s %}
|
|
; RUN: %if aarch64-registered-target %{ opt -S --passes=slp-vectorizer -slp-threshold=-10 < %s -mtriple=aarch64-unknown-linux-gnu | FileCheck %s %}
|
|
|
|
define void @test(ptr %0) {
|
|
; CHECK-LABEL: define void @test(
|
|
; CHECK-SAME: ptr [[TMP0:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x ptr> <ptr null, ptr poison>, ptr [[TMP0]], i32 1
|
|
; CHECK-NEXT: [[TMP2:%.*]] = ptrtoint <2 x ptr> [[TMP1]] to <2 x i64>
|
|
; CHECK-NEXT: [[TMP8:%.*]] = ptrtoint ptr [[TMP0]] to i64
|
|
; CHECK-NEXT: [[TMP5:%.*]] = trunc i64 [[TMP8]] to i32
|
|
; CHECK-NEXT: [[TMP6:%.*]] = ptrtoint ptr null to i64
|
|
; CHECK-NEXT: [[TMP3:%.*]] = trunc <2 x i64> [[TMP2]] to <2 x i32>
|
|
; CHECK-NEXT: switch i32 0, label %[[NEWFUNCROOT994:.*]] [
|
|
; CHECK-NEXT: i32 1, label %[[NEWFUNCROOT994]]
|
|
; CHECK-NEXT: i32 0, label %[[NEWFUNCROOT584:.*]]
|
|
; CHECK-NEXT: ]
|
|
; CHECK: [[NEWFUNCROOT584]]:
|
|
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
|
|
; CHECK-NEXT: ret void
|
|
; CHECK: [[NEWFUNCROOT994]]:
|
|
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x i32> zeroinitializer, i32 [[TMP5]], i64 [[TMP6]]
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%1 = ptrtoint ptr %0 to i64
|
|
%2 = trunc i64 %1 to i32
|
|
%3 = ptrtoint ptr null to i64
|
|
%4 = trunc i64 %3 to i32
|
|
switch i32 0, label %newFuncRoot994 [
|
|
i32 1, label %newFuncRoot994
|
|
i32 0, label %newFuncRoot584
|
|
]
|
|
|
|
newFuncRoot584:
|
|
%5 = insertelement <4 x i32> poison, i32 %4, i64 0
|
|
%6 = insertelement <4 x i32> %5, i32 %2, i64 1
|
|
ret void
|
|
|
|
newFuncRoot994:
|
|
%7 = insertelement <4 x i32> zeroinitializer, i32 %2, i64 %3
|
|
ret void
|
|
}
|