28 lines
1.3 KiB
LLVM
28 lines
1.3 KiB
LLVM
; 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
|
|
}
|