2016-08-13 04:39:51 +08:00
|
|
|
; RUN: llc -mcpu cortex-a53 < %s | FileCheck %s
|
|
|
|
|
target datalayout = "e-m:e-i64:64-i128:128-n8:16:32:64-S128"
|
|
|
|
|
target triple = "aarch64--linux-gnu"
|
|
|
|
|
|
|
|
|
|
declare void @f(i8*, i8*)
|
|
|
|
|
declare void @f2(i8*, i8*)
|
|
|
|
|
declare void @_Z5setupv()
|
|
|
|
|
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) #3
|
|
|
|
|
|
|
|
|
|
define i32 @main() local_unnamed_addr #1 {
|
|
|
|
|
; Make sure the stores happen in the correct order (the exact instructions could change).
|
|
|
|
|
; CHECK-LABEL: main:
|
[AArch64] Split 0 vector stores into scalar store pairs.
Summary:
Replace a splat of zeros to a vector store by scalar stores of WZR/XZR.
The load store optimizer pass will merge them to store pair stores.
This should be better than a movi to create the vector zero followed by
a vector store if the zero constant is not re-used, since one
instructions and one register live range will be removed.
For example, the final generated code should be:
stp xzr, xzr, [x0]
instead of:
movi v0.2d, #0
str q0, [x0]
Reviewers: t.p.northover, mcrosier, MatzeB, jmolloy
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: https://reviews.llvm.org/D26561
llvm-svn: 286875
2016-11-15 03:39:04 +08:00
|
|
|
; CHECK: stp xzr, xzr, [sp, #72]
|
|
|
|
|
; CHECK: str w9, [sp, #80]
|
2016-08-13 04:39:51 +08:00
|
|
|
; CHECK: str q0, [sp, #48]
|
|
|
|
|
; CHECK: ldr w8, [sp, #48]
|
|
|
|
|
; CHECK: str q0, [sp, #64]
|
|
|
|
|
|
|
|
|
|
for.body.lr.ph.i.i.i.i.i.i63:
|
|
|
|
|
%b1 = alloca [10 x i32], align 16
|
|
|
|
|
%x0 = bitcast [10 x i32]* %b1 to i8*
|
|
|
|
|
%b2 = alloca [10 x i32], align 16
|
|
|
|
|
%x1 = bitcast [10 x i32]* %b2 to i8*
|
|
|
|
|
tail call void @_Z5setupv()
|
|
|
|
|
%x2 = getelementptr inbounds [10 x i32], [10 x i32]* %b1, i64 0, i64 6
|
|
|
|
|
%x3 = bitcast i32* %x2 to i8*
|
|
|
|
|
call void @llvm.memset.p0i8.i64(i8* %x3, i8 0, i64 16, i32 8, i1 false)
|
|
|
|
|
%arraydecay2 = getelementptr inbounds [10 x i32], [10 x i32]* %b1, i64 0, i64 0
|
|
|
|
|
%x4 = bitcast [10 x i32]* %b1 to <4 x i32>*
|
|
|
|
|
store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32>* %x4, align 16
|
|
|
|
|
%incdec.ptr.i7.i.i.i.i.i.i64.3 = getelementptr inbounds [10 x i32], [10 x i32]* %b1, i64 0, i64 4
|
|
|
|
|
%x5 = bitcast i32* %incdec.ptr.i7.i.i.i.i.i.i64.3 to <4 x i32>*
|
|
|
|
|
store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32>* %x5, align 16
|
|
|
|
|
%incdec.ptr.i7.i.i.i.i.i.i64.7 = getelementptr inbounds [10 x i32], [10 x i32]* %b1, i64 0, i64 8
|
|
|
|
|
store i32 1, i32* %incdec.ptr.i7.i.i.i.i.i.i64.7, align 16
|
|
|
|
|
%x6 = load i32, i32* %arraydecay2, align 16
|
|
|
|
|
%cmp6 = icmp eq i32 %x6, 1
|
|
|
|
|
br i1 %cmp6, label %for.inc, label %if.then
|
|
|
|
|
|
|
|
|
|
for.inc:
|
|
|
|
|
call void @f(i8* %x0, i8* %x1)
|
|
|
|
|
ret i32 0
|
|
|
|
|
|
|
|
|
|
if.then:
|
|
|
|
|
call void @f2(i8* %x0, i8* %x1)
|
|
|
|
|
ret i32 0
|
|
|
|
|
}
|
