mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-28 19:31:58 +00:00
2b1874cbd4
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218922 91177308-0d34-0410-b5e6-96231b3b80d8
82 lines
2.7 KiB
LLVM
82 lines
2.7 KiB
LLVM
; RUN: llc < %s -mtriple=powerpc-apple-darwin -march=ppc32 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=PPC32
|
|
; FIXME: -verify-machineinstrs currently fail on ppc64 (mismatched register/instruction).
|
|
; This is already checked for in Atomics-64.ll
|
|
; RUN: llc < %s -mtriple=powerpc-apple-darwin -march=ppc64 | FileCheck %s --check-prefix=CHECK --check-prefix=PPC64
|
|
|
|
; In this file, we check that atomic load/store can make use of the indexed
|
|
; versions of the instructions.
|
|
|
|
; Indexed version of loads
|
|
define i8 @load_x_i8_seq_cst([100000 x i8]* %mem) {
|
|
; CHECK-LABEL: load_x_i8_seq_cst
|
|
; CHECK: sync 0
|
|
; CHECK: lbzx
|
|
; CHECK: sync 1
|
|
%ptr = getelementptr inbounds [100000 x i8]* %mem, i64 0, i64 90000
|
|
%val = load atomic i8* %ptr seq_cst, align 1
|
|
ret i8 %val
|
|
}
|
|
define i16 @load_x_i16_acquire([100000 x i16]* %mem) {
|
|
; CHECK-LABEL: load_x_i16_acquire
|
|
; CHECK: lhzx
|
|
; CHECK: sync 1
|
|
%ptr = getelementptr inbounds [100000 x i16]* %mem, i64 0, i64 90000
|
|
%val = load atomic i16* %ptr acquire, align 2
|
|
ret i16 %val
|
|
}
|
|
define i32 @load_x_i32_monotonic([100000 x i32]* %mem) {
|
|
; CHECK-LABEL: load_x_i32_monotonic
|
|
; CHECK: lwzx
|
|
; CHECK-NOT: sync
|
|
%ptr = getelementptr inbounds [100000 x i32]* %mem, i64 0, i64 90000
|
|
%val = load atomic i32* %ptr monotonic, align 4
|
|
ret i32 %val
|
|
}
|
|
define i64 @load_x_i64_unordered([100000 x i64]* %mem) {
|
|
; CHECK-LABEL: load_x_i64_unordered
|
|
; PPC32: __sync_
|
|
; PPC64-NOT: __sync_
|
|
; PPC64: ldx
|
|
; CHECK-NOT: sync
|
|
%ptr = getelementptr inbounds [100000 x i64]* %mem, i64 0, i64 90000
|
|
%val = load atomic i64* %ptr unordered, align 8
|
|
ret i64 %val
|
|
}
|
|
|
|
; Indexed version of stores
|
|
define void @store_x_i8_seq_cst([100000 x i8]* %mem) {
|
|
; CHECK-LABEL: store_x_i8_seq_cst
|
|
; CHECK: sync 0
|
|
; CHECK: stbx
|
|
%ptr = getelementptr inbounds [100000 x i8]* %mem, i64 0, i64 90000
|
|
store atomic i8 42, i8* %ptr seq_cst, align 1
|
|
ret void
|
|
}
|
|
define void @store_x_i16_release([100000 x i16]* %mem) {
|
|
; CHECK-LABEL: store_x_i16_release
|
|
; CHECK: sync 1
|
|
; CHECK: sthx
|
|
%ptr = getelementptr inbounds [100000 x i16]* %mem, i64 0, i64 90000
|
|
store atomic i16 42, i16* %ptr release, align 2
|
|
ret void
|
|
}
|
|
define void @store_x_i32_monotonic([100000 x i32]* %mem) {
|
|
; CHECK-LABEL: store_x_i32_monotonic
|
|
; CHECK-NOT: sync
|
|
; CHECK: stwx
|
|
%ptr = getelementptr inbounds [100000 x i32]* %mem, i64 0, i64 90000
|
|
store atomic i32 42, i32* %ptr monotonic, align 4
|
|
ret void
|
|
}
|
|
define void @store_x_i64_unordered([100000 x i64]* %mem) {
|
|
; CHECK-LABEL: store_x_i64_unordered
|
|
; CHECK-NOT: sync 0
|
|
; CHECK-NOT: sync 1
|
|
; PPC32: __sync_
|
|
; PPC64-NOT: __sync_
|
|
; PPC64: stdx
|
|
%ptr = getelementptr inbounds [100000 x i64]* %mem, i64 0, i64 90000
|
|
store atomic i64 42, i64* %ptr unordered, align 8
|
|
ret void
|
|
}
|