Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
------------------------------------------------------------------------ r322106 | abataev | 2018-01-09 11:08:22 -0800 (Tue, 09 Jan 2018) | 11 lines [COST]Fix PR35865: Fix cost model evaluation for shuffle on X86. Summary: If the vector type is transformed to non-vector single type, the compile may crash trying to get vector information about non-vector type. Reviewers: RKSimon, spatel, mkuper, hfinkel Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41862 ------------------------------------------------------------------------ llvm-svn: 322680
- Loading branch information
Showing
2 changed files
with
29 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,27 @@ | ||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py | ||
; RUN: opt -slp-vectorizer < %s -S -o - -mtriple=x86_64-apple-macosx10.10.0 -mcpu=core2 | FileCheck %s | ||
|
||
define void @_Z10fooConvertPDv4_xS0_S0_PKS_() { | ||
; CHECK-LABEL: @_Z10fooConvertPDv4_xS0_S0_PKS_( | ||
; CHECK-NEXT: entry: | ||
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <16 x half> undef, i32 4 | ||
; CHECK-NEXT: [[CONV_I_4_I:%.*]] = fpext half [[TMP0]] to float | ||
; CHECK-NEXT: [[TMP1:%.*]] = bitcast float [[CONV_I_4_I]] to i32 | ||
; CHECK-NEXT: [[VECINS_I_4_I:%.*]] = insertelement <8 x i32> undef, i32 [[TMP1]], i32 4 | ||
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <16 x half> undef, i32 5 | ||
; CHECK-NEXT: [[CONV_I_5_I:%.*]] = fpext half [[TMP2]] to float | ||
; CHECK-NEXT: [[TMP3:%.*]] = bitcast float [[CONV_I_5_I]] to i32 | ||
; CHECK-NEXT: [[VECINS_I_5_I:%.*]] = insertelement <8 x i32> [[VECINS_I_4_I]], i32 [[TMP3]], i32 5 | ||
; CHECK-NEXT: ret void | ||
; | ||
entry: | ||
%0 = extractelement <16 x half> undef, i32 4 | ||
%conv.i.4.i = fpext half %0 to float | ||
%1 = bitcast float %conv.i.4.i to i32 | ||
%vecins.i.4.i = insertelement <8 x i32> undef, i32 %1, i32 4 | ||
%2 = extractelement <16 x half> undef, i32 5 | ||
%conv.i.5.i = fpext half %2 to float | ||
%3 = bitcast float %conv.i.5.i to i32 | ||
%vecins.i.5.i = insertelement <8 x i32> %vecins.i.4.i, i32 %3, i32 5 | ||
ret void | ||
} |