300e1293de
We are going to remove the old 'perfect shuffle' optimization since it brings performance penalty in hot loop around vectors. For example, in following loop sharing the same mask: %v.1 = shufflevector ... <0,1,2,3,8,9,10,11,16,17,18,19,24,25,26,27> %v.2 = shufflevector ... <0,1,2,3,8,9,10,11,16,17,18,19,24,25,26,27> The generated instructions will be `vmrglw-vmrghw-vmrglw-vmrghw` instead of `vperm-vperm`. In some large loop cases, this causes 20%+ performance penalty. The original attempt to resolve this is to pre-record masks of every shufflevector operation in DAG, but that is somewhat complex and brings unnecessary computation (to scan all nodes) in optimization. Here we disable it by default. There're indeed some cases becoming worse after this, which will be fixed in a more careful way in future patches. Reviewed By: jsji Differential Revision: https://reviews.llvm.org/D121082
207 lines
5.7 KiB
LLVM
207 lines
5.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-gnu-linux -mcpu=pwr9 < %s | FileCheck %s -check-prefix=CHECK-LE
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-gnu-linux -mcpu=pwr9 < %s | FileCheck %s -check-prefix=CHECK-BE
|
|
|
|
define zeroext i8 @test1(<16 x i8> %a, i32 signext %index) {
|
|
; CHECK-LE-LABEL: test1:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: vextubrx 3, 5, 2
|
|
; CHECK-LE-NEXT: clrldi 3, 3, 56
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test1:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: vextublx 3, 5, 2
|
|
; CHECK-BE-NEXT: clrldi 3, 3, 56
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <16 x i8> %a, i32 %index
|
|
ret i8 %vecext
|
|
}
|
|
|
|
define signext i8 @test2(<16 x i8> %a, i32 signext %index) {
|
|
; CHECK-LE-LABEL: test2:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: vextubrx 3, 5, 2
|
|
; CHECK-LE-NEXT: extsb 3, 3
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test2:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: vextublx 3, 5, 2
|
|
; CHECK-BE-NEXT: extsb 3, 3
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <16 x i8> %a, i32 %index
|
|
ret i8 %vecext
|
|
}
|
|
|
|
define zeroext i16 @test3(<8 x i16> %a, i32 signext %index) {
|
|
; CHECK-LE-LABEL: test3:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: rlwinm 3, 5, 1, 28, 30
|
|
; CHECK-LE-NEXT: vextuhrx 3, 3, 2
|
|
; CHECK-LE-NEXT: clrldi 3, 3, 48
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test3:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: rlwinm 3, 5, 1, 28, 30
|
|
; CHECK-BE-NEXT: vextuhlx 3, 3, 2
|
|
; CHECK-BE-NEXT: clrldi 3, 3, 48
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <8 x i16> %a, i32 %index
|
|
ret i16 %vecext
|
|
}
|
|
|
|
define signext i16 @test4(<8 x i16> %a, i32 signext %index) {
|
|
; CHECK-LE-LABEL: test4:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: rlwinm 3, 5, 1, 28, 30
|
|
; CHECK-LE-NEXT: vextuhrx 3, 3, 2
|
|
; CHECK-LE-NEXT: extsh 3, 3
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test4:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: rlwinm 3, 5, 1, 28, 30
|
|
; CHECK-BE-NEXT: vextuhlx 3, 3, 2
|
|
; CHECK-BE-NEXT: extsh 3, 3
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <8 x i16> %a, i32 %index
|
|
ret i16 %vecext
|
|
}
|
|
|
|
define zeroext i32 @test5(<4 x i32> %a, i32 signext %index) {
|
|
; CHECK-LE-LABEL: test5:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: rlwinm 3, 5, 2, 28, 29
|
|
; CHECK-LE-NEXT: vextuwrx 3, 3, 2
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test5:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: rlwinm 3, 5, 2, 28, 29
|
|
; CHECK-BE-NEXT: vextuwlx 3, 3, 2
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <4 x i32> %a, i32 %index
|
|
ret i32 %vecext
|
|
}
|
|
|
|
define signext i32 @test6(<4 x i32> %a, i32 signext %index) {
|
|
; CHECK-LE-LABEL: test6:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: rlwinm 3, 5, 2, 28, 29
|
|
; CHECK-LE-NEXT: vextuwrx 3, 3, 2
|
|
; CHECK-LE-NEXT: extsw 3, 3
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test6:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: rlwinm 3, 5, 2, 28, 29
|
|
; CHECK-BE-NEXT: vextuwlx 3, 3, 2
|
|
; CHECK-BE-NEXT: extsw 3, 3
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <4 x i32> %a, i32 %index
|
|
ret i32 %vecext
|
|
}
|
|
|
|
; Test with immediate index
|
|
define zeroext i8 @test7(<16 x i8> %a) {
|
|
; CHECK-LE-LABEL: test7:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: li 3, 1
|
|
; CHECK-LE-NEXT: vextubrx 3, 3, 2
|
|
; CHECK-LE-NEXT: clrldi 3, 3, 56
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test7:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: li 3, 1
|
|
; CHECK-BE-NEXT: vextublx 3, 3, 2
|
|
; CHECK-BE-NEXT: clrldi 3, 3, 56
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <16 x i8> %a, i32 1
|
|
ret i8 %vecext
|
|
}
|
|
|
|
define zeroext i16 @test8(<8 x i16> %a) {
|
|
; CHECK-LE-LABEL: test8:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: li 3, 2
|
|
; CHECK-LE-NEXT: vextuhrx 3, 3, 2
|
|
; CHECK-LE-NEXT: clrldi 3, 3, 48
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test8:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: li 3, 2
|
|
; CHECK-BE-NEXT: vextuhlx 3, 3, 2
|
|
; CHECK-BE-NEXT: clrldi 3, 3, 48
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <8 x i16> %a, i32 1
|
|
ret i16 %vecext
|
|
}
|
|
|
|
define zeroext i32 @test9(<4 x i32> %a) {
|
|
; CHECK-LE-LABEL: test9:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: li 3, 12
|
|
; CHECK-LE-NEXT: vextuwrx 3, 3, 2
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test9:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: li 3, 12
|
|
; CHECK-BE-NEXT: vextuwlx 3, 3, 2
|
|
; CHECK-BE-NEXT: blr
|
|
|
|
entry:
|
|
%vecext = extractelement <4 x i32> %a, i32 3
|
|
ret i32 %vecext
|
|
}
|
|
|
|
define double @test10(<4 x i32> %a, <4 x i32> %b) {
|
|
; CHECK-LE-LABEL: test10:
|
|
; CHECK-LE: # %bb.0: # %entry
|
|
; CHECK-LE-NEXT: addis 3, 2, .LCPI9_0@toc@ha
|
|
; CHECK-LE-NEXT: addi 3, 3, .LCPI9_0@toc@l
|
|
; CHECK-LE-NEXT: lxv 36, 0(3)
|
|
; CHECK-LE-NEXT: addis 3, 2, .LCPI9_1@toc@ha
|
|
; CHECK-LE-NEXT: lfs 0, .LCPI9_1@toc@l(3)
|
|
; CHECK-LE-NEXT: vperm 2, 3, 2, 4
|
|
; CHECK-LE-NEXT: xsadddp 1, 34, 0
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: test10:
|
|
; CHECK-BE: # %bb.0: # %entry
|
|
; CHECK-BE-NEXT: addis 3, 2, .LCPI9_0@toc@ha
|
|
; CHECK-BE-NEXT: addi 3, 3, .LCPI9_0@toc@l
|
|
; CHECK-BE-NEXT: lxv 36, 0(3)
|
|
; CHECK-BE-NEXT: addis 3, 2, .LCPI9_1@toc@ha
|
|
; CHECK-BE-NEXT: lfs 0, .LCPI9_1@toc@l(3)
|
|
; CHECK-BE-NEXT: vperm 2, 3, 2, 4
|
|
; CHECK-BE-NEXT: xsadddp 1, 34, 0
|
|
; CHECK-BE-NEXT: blr
|
|
entry:
|
|
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 5, i32 2, i32 3, i32 7>
|
|
%cast = bitcast <4 x i32> %shuffle to <2 x double>
|
|
%extract = extractelement <2 x double> %cast, i32 0
|
|
%add = fadd double %extract, 1.0000
|
|
ret double %add
|
|
}
|