2013-04-02 20:37:08 +02:00
|
|
|
; RUN: llc -mcpu=pwr7 -O0 < %s | FileCheck %s
|
|
|
|
|
|
|
|
|
|
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64"
|
|
|
|
|
target triple = "powerpc64-unknown-linux-gnu"
|
|
|
|
|
|
|
|
|
|
define weak_odr void @_D4core6atomic49__T11atomicStoreVE4core6atomic11MemoryOrder3ThThZ11atomicStoreFNaNbKOhhZv(i8* %val_arg, i8 zeroext %newval_arg) {
|
|
|
|
|
entry:
|
|
|
|
|
%newval = alloca i8
|
|
|
|
|
%ordering = alloca i32, align 4
|
|
|
|
|
store i8 %newval_arg, i8* %newval
|
|
|
|
|
%tmp = load i8* %newval
|
|
|
|
|
store atomic volatile i8 %tmp, i8* %val_arg seq_cst, align 1
|
|
|
|
|
ret void
|
|
|
|
|
}
|
|
|
|
|
|
[Power] Improve the expansion of atomic loads/stores
Summary:
Atomic loads and store of up to the native size (32 bits, or 64 for PPC64)
can be lowered to a simple load or store instruction (as the synchronization
is already handled by AtomicExpand, and the atomicity is guaranteed thanks to
the alignment requirements of atomic accesses). This is exactly what this patch
does. Previously, these were implemented by complex
load-linked/store-conditional loops.. an obvious performance problem.
For example, this patch turns
```
define void @store_i8_unordered(i8* %mem) {
store atomic i8 42, i8* %mem unordered, align 1
ret void
}
```
from
```
_store_i8_unordered: ; @store_i8_unordered
; BB#0:
rlwinm r2, r3, 3, 27, 28
li r4, 42
xori r5, r2, 24
rlwinm r2, r3, 0, 0, 29
li r3, 255
slw r4, r4, r5
slw r3, r3, r5
and r4, r4, r3
LBB4_1: ; =>This Inner Loop Header: Depth=1
lwarx r5, 0, r2
andc r5, r5, r3
or r5, r4, r5
stwcx. r5, 0, r2
bne cr0, LBB4_1
; BB#2:
blr
```
into
```
_store_i8_unordered: ; @store_i8_unordered
; BB#0:
li r2, 42
stb r2, 0(r3)
blr
```
which looks like a pretty clear win to me.
Test Plan:
fixed the tests + new test for indexed accesses + make check-all
Reviewers: jfb, wschmidt, hfinkel
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5587
llvm-svn: 218922
2014-10-03 00:27:07 +02:00
|
|
|
; CHECK: sync
|
|
|
|
|
; CHECK: stb
|
