replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[SLP] Fix invalid triple in X86 tests 

x86-64 is an invalid architecture in triples. Changing it to the correct
triple (x86_64) changes some tests, because SLP is not deemed profitable
any more.

Reviewers: ABataev, RKSimon, spatel

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D58931

llvm-svn: 355420
This commit is contained in:
Florian Hahn 2019-03-05 17:56:35 +00:00
parent 071949c3af
commit add2d2e304
2 changed files with 37 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
View File

@ -1,11 +1,15 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S -o - -mtriple=x86-64-unknown-linux -mcpu=bdver2 -instcombine | FileCheck %s
; RUN: opt < %s -slp-vectorizer -S -o - -mtriple=x86_64-unknown-linux -mcpu=bdver2 -instcombine | FileCheck %s
define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
; CHECK-LABEL: @g(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
; CHECK-NEXT: ret <2 x i8> [[TMP2]]
; CHECK-NEXT: [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
; CHECK-NEXT: [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT: [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[X0X0]], i32 0
; CHECK-NEXT: [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
; CHECK-NEXT: ret <2 x i8> [[INS2]]
;
%x0 = extractelement <2 x i8> %x, i32 0
%y1 = extractelement <2 x i8> %y, i32 1
@ -85,15 +89,18 @@ define i8 @i(<4 x i8> %x, <4 x i8> %y) {
define i8 @j(<4 x i8> %x, <4 x i8> %y) {
; CHECK-LABEL: @j(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i8> [[X:%.*]], <4 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 5>
; CHECK-NEXT: [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i8> [[X]], <4 x i8> [[Y]], <2 x i32> <i32 3, i32 6>
; CHECK-NEXT: [[TMP4:%.*]] = mul <2 x i8> [[TMP3]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i32 1
; CHECK-NEXT: [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
; CHECK-NEXT: ret i8 [[TMP8]]
; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
; CHECK-NEXT: [[Y1:%.*]] = extractelement <4 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT: [[Y2:%.*]] = extractelement <4 x i8> [[Y]], i32 2
; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT: [[Y2Y2:%.*]] = mul i8 [[Y2]], [[Y2]]
; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[Y1Y1]], [[Y2Y2]]
; CHECK-NEXT: [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret i8 [[TMP3]]
;
%x0 = extractelement <4 x i8> %x, i32 0
%x3 = extractelement <4 x i8> %x, i32 3
@ -111,15 +118,18 @@ define i8 @j(<4 x i8> %x, <4 x i8> %y) {
define i8 @k(<4 x i8> %x) {
; CHECK-LABEL: @k(
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i8> [[X:%.*]], [[X]]
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> undef, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = mul <4 x i8> [[X]], [[X]]
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> undef, <2 x i32> <i32 3, i32 2>
; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i32 1
; CHECK-NEXT: [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
; CHECK-NEXT: ret i8 [[TMP8]]
; CHECK-NEXT: [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i32 0
; CHECK-NEXT: [[X3:%.*]] = extractelement <4 x i8> [[X]], i32 3
; CHECK-NEXT: [[X1:%.*]] = extractelement <4 x i8> [[X]], i32 1
; CHECK-NEXT: [[X2:%.*]] = extractelement <4 x i8> [[X]], i32 2
; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT: [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
; CHECK-NEXT: [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
; CHECK-NEXT: [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
; CHECK-NEXT: [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
; CHECK-NEXT: [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
; CHECK-NEXT: [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret i8 [[TMP3]]
;
%x0 = extractelement <4 x i8> %x, i32 0
%x3 = extractelement <4 x i8> %x, i32 3

13
llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
View File

@ -1,17 +1,14 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S -o - -mtriple=x86-64-unknown-linux -mcpu=bdver2 -slp-schedule-budget=1 | FileCheck %s
; RUN: opt < %s -slp-vectorizer -S -o - -mtriple=x86_64-unknown-linux -mcpu=bdver2 -slp-schedule-budget=1 | FileCheck %s
define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
; CHECK-LABEL: @g(
; CHECK-NEXT: [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
; CHECK-NEXT: [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i8> undef, i8 [[X0]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x i8> [[TMP1]], i8 [[Y1]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = mul <2 x i8> [[TMP2]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <2 x i8> [[TMP3]], i32 0
; CHECK-NEXT: [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[TMP4]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <2 x i8> [[TMP3]], i32 1
; CHECK-NEXT: [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[TMP5]], i32 1
; CHECK-NEXT: [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
; CHECK-NEXT: [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
; CHECK-NEXT: [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[X0X0]], i32 0
; CHECK-NEXT: [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
; CHECK-NEXT: ret <2 x i8> [[INS2]]
;
%x0 = extractelement <2 x i8> %x, i32 0