1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=slp-vectorizer,instcombine -S | FileCheck %s
; Regression test for a bug in the SLP vectorizer that was causing
; these rotates to be incorrectly combined into a vector rotate.
target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
target triple = "wasm32-unknown-unknown"
define void @foo(<2 x i64> %x, <4 x i32> %y, ptr %out) #0 {
; CHECK-LABEL: @foo(
; CHECK-NEXT: [[A:%.*]] = extractelement <2 x i64> [[X:%.*]], i64 0
; CHECK-NEXT: [[B:%.*]] = extractelement <4 x i32> [[Y:%.*]], i64 2
; CHECK-NEXT: [[CONV6:%.*]] = zext i32 [[B]] to i64
; CHECK-NEXT: [[C:%.*]] = tail call i64 @llvm.fshl.i64(i64 [[A]], i64 [[A]], i64 [[CONV6]])
; CHECK-NEXT: store i64 [[C]], ptr [[OUT:%.*]], align 8
; CHECK-NEXT: [[D:%.*]] = extractelement <2 x i64> [[X]], i64 1
; CHECK-NEXT: [[E:%.*]] = extractelement <4 x i32> [[Y]], i64 3
; CHECK-NEXT: [[CONV17:%.*]] = zext i32 [[E]] to i64
; CHECK-NEXT: [[F:%.*]] = tail call i64 @llvm.fshl.i64(i64 [[D]], i64 [[D]], i64 [[CONV17]])
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds nuw i8, ptr [[OUT]], i32 8
; CHECK-NEXT: store i64 [[F]], ptr [[ARRAYIDX2]], align 8
; CHECK-NEXT: ret void
;
%a = extractelement <2 x i64> %x, i32 0
%b = extractelement <4 x i32> %y, i32 2
%conv6 = zext i32 %b to i64
%c = tail call i64 @llvm.fshl.i64(i64 %a, i64 %a, i64 %conv6)
store i64 %c, ptr %out
%d = extractelement <2 x i64> %x, i32 1
%e = extractelement <4 x i32> %y, i32 3
%conv17 = zext i32 %e to i64
%f = tail call i64 @llvm.fshl.i64(i64 %d, i64 %d, i64 %conv17)
%arrayidx2 = getelementptr inbounds i64, ptr %out, i32 1
store i64 %f, ptr %arrayidx2
ret void
}
declare i64 @llvm.fshl.i64(i64, i64, i64)
attributes #0 = {"target-cpu"="generic" "target-features"="+simd128"}
|
