forked from OSchip/llvm-project
[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
This commit is contained in:
Robin Morisset
parent
7425c8c279
commit
e1ca44bd4c
|
|
@ -613,10 +613,10 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM)
|
|||
setOperationAction(ISD::READCYCLECOUNTER, MVT::i64, Legal);
|
||||
}
|
||||
|
||||
setOperationAction(ISD::ATOMIC_LOAD, MVT::i32, Expand);
|
||||
setOperationAction(ISD::ATOMIC_STORE, MVT::i32, Expand);
|
||||
setOperationAction(ISD::ATOMIC_LOAD, MVT::i64, Expand);
|
||||
setOperationAction(ISD::ATOMIC_STORE, MVT::i64, Expand);
|
||||
if (!isPPC64) {
|
||||
setOperationAction(ISD::ATOMIC_LOAD, MVT::i64, Expand);
|
||||
setOperationAction(ISD::ATOMIC_STORE, MVT::i64, Expand);
|
||||
}
|
||||
|
||||
setBooleanContents(ZeroOrOneBooleanContent);
|
||||
// Altivec instructions set fields to all zeros or all ones.
|
||||
|
|
|
|||
|
|
@ -1135,3 +1135,9 @@ def : Pat<(i64 (unaligned4load xoaddr:$src)),
|
|||
def : Pat<(unaligned4store i64:$rS, xoaddr:$dst),
|
||||
(STDX $rS, xoaddr:$dst)>;
|
||||
|
||||
// 64-bits atomic loads and stores
|
||||
def : Pat<(atomic_load_64 ixaddr:$src), (LD memrix:$src)>;
|
||||
def : Pat<(atomic_load_64 xaddr:$src), (LDX memrr:$src)>;
|
||||
|
||||
def : Pat<(atomic_store_64 ixaddr:$ptr, i64:$val), (STD g8rc:$val, memrix:$ptr)>;
|
||||
def : Pat<(atomic_store_64 xaddr:$ptr, i64:$val), (STDX g8rc:$val, memrr:$ptr)>;
|
||||
|
|
|
|||
|
|
@ -3695,3 +3695,19 @@ defm : TrapExtendedMnemonic<"lgt", 1>;
|
|||
defm : TrapExtendedMnemonic<"lnl", 5>;
|
||||
defm : TrapExtendedMnemonic<"lng", 6>;
|
||||
defm : TrapExtendedMnemonic<"u", 31>;
|
||||
|
||||
// Atomic loads
|
||||
def : Pat<(atomic_load_8 iaddr:$src), (LBZ memri:$src)>;
|
||||
def : Pat<(atomic_load_16 iaddr:$src), (LHZ memri:$src)>;
|
||||
def : Pat<(atomic_load_32 iaddr:$src), (LWZ memri:$src)>;
|
||||
def : Pat<(atomic_load_8 xaddr:$src), (LBZX memrr:$src)>;
|
||||
def : Pat<(atomic_load_16 xaddr:$src), (LHZX memrr:$src)>;
|
||||
def : Pat<(atomic_load_32 xaddr:$src), (LWZX memrr:$src)>;
|
||||
|
||||
// Atomic stores
|
||||
def : Pat<(atomic_store_8 iaddr:$ptr, i32:$val), (STB gprc:$val, memri:$ptr)>;
|
||||
def : Pat<(atomic_store_16 iaddr:$ptr, i32:$val), (STH gprc:$val, memri:$ptr)>;
|
||||
def : Pat<(atomic_store_32 iaddr:$ptr, i32:$val), (STW gprc:$val, memri:$ptr)>;
|
||||
def : Pat<(atomic_store_8 xaddr:$ptr, i32:$val), (STBX gprc:$val, memrr:$ptr)>;
|
||||
def : Pat<(atomic_store_16 xaddr:$ptr, i32:$val), (STHX gprc:$val, memrr:$ptr)>;
|
||||
def : Pat<(atomic_store_32 xaddr:$ptr, i32:$val), (STWX gprc:$val, memrr:$ptr)>;
|
||||
|
|
|
|||
|
|
@ -30,8 +30,9 @@ define void @atomic_store(i64* %mem, i64 %val) nounwind {
|
|||
entry:
|
||||
; CHECK: @atomic_store
|
||||
store atomic i64 %val, i64* %mem release, align 64
|
||||
; CHECK: ldarx
|
||||
; CHECK: stdcx.
|
||||
; CHECK: sync 1
|
||||
; CHECK-NOT: stdcx
|
||||
; CHECK: std
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -39,9 +40,9 @@ define i64 @atomic_load(i64* %mem) nounwind {
|
|||
entry:
|
||||
; CHECK: @atomic_load
|
||||
%tmp = load atomic i64* %mem acquire, align 64
|
||||
; CHECK: ldarx
|
||||
; CHECK: stdcx.
|
||||
; CHECK: stdcx.
|
||||
; CHECK-NOT: ldarx
|
||||
; CHECK: ld
|
||||
; CHECK: sync 1
|
||||
ret i64 %tmp
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,81 @@
|
|||
; 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
|
||||
}
|
||||
|
|
@ -11,18 +11,21 @@
|
|||
; We also vary orderings to check for barriers.
|
||||
define i8 @load_i8_unordered(i8* %mem) {
|
||||
; CHECK-LABEL: load_i8_unordered
|
||||
; CHECK: lbz
|
||||
; CHECK-NOT: sync
|
||||
%val = load atomic i8* %mem unordered, align 1
|
||||
ret i8 %val
|
||||
}
|
||||
define i16 @load_i16_monotonic(i16* %mem) {
|
||||
; CHECK-LABEL: load_i16_monotonic
|
||||
; CHECK: lhz
|
||||
; CHECK-NOT: sync
|
||||
%val = load atomic i16* %mem monotonic, align 2
|
||||
ret i16 %val
|
||||
}
|
||||
define i32 @load_i32_acquire(i32* %mem) {
|
||||
; CHECK-LABEL: load_i32_acquire
|
||||
; CHECK: lwz
|
||||
%val = load atomic i32* %mem acquire, align 4
|
||||
; CHECK: sync 1
|
||||
ret i32 %val
|
||||
|
|
@ -30,6 +33,9 @@ define i32 @load_i32_acquire(i32* %mem) {
|
|||
define i64 @load_i64_seq_cst(i64* %mem) {
|
||||
; CHECK-LABEL: load_i64_seq_cst
|
||||
; CHECK: sync 0
|
||||
; PPC32: __sync_
|
||||
; PPC64-NOT: __sync_
|
||||
; PPC64: ld
|
||||
%val = load atomic i64* %mem seq_cst, align 8
|
||||
; CHECK: sync 1
|
||||
ret i64 %val
|
||||
|
|
@ -39,24 +45,30 @@ define i64 @load_i64_seq_cst(i64* %mem) {
|
|||
define void @store_i8_unordered(i8* %mem) {
|
||||
; CHECK-LABEL: store_i8_unordered
|
||||
; CHECK-NOT: sync
|
||||
; CHECK: stb
|
||||
store atomic i8 42, i8* %mem unordered, align 1
|
||||
ret void
|
||||
}
|
||||
define void @store_i16_monotonic(i16* %mem) {
|
||||
; CHECK-LABEL: store_i16_monotonic
|
||||
; CHECK-NOT: sync
|
||||
; CHECK: sth
|
||||
store atomic i16 42, i16* %mem monotonic, align 2
|
||||
ret void
|
||||
}
|
||||
define void @store_i32_release(i32* %mem) {
|
||||
; CHECK-LABEL: store_i32_release
|
||||
; CHECK: sync 1
|
||||
; CHECK: stw
|
||||
store atomic i32 42, i32* %mem release, align 4
|
||||
ret void
|
||||
}
|
||||
define void @store_i64_seq_cst(i64* %mem) {
|
||||
; CHECK-LABEL: store_i64_seq_cst
|
||||
; CHECK: sync 0
|
||||
; PPC32: __sync_
|
||||
; PPC64-NOT: __sync_
|
||||
; PPC64: std
|
||||
store atomic i64 42, i64* %mem seq_cst, align 8
|
||||
ret void
|
||||
}
|
||||
|
|
|
|||
|
|
@ -13,4 +13,5 @@ entry:
|
|||
ret void
|
||||
}
|
||||
|
||||
; CHECK: stwcx.
|
||||
; CHECK: sync
|
||||
; CHECK: stb
|
||||
|
|
|
|||
Loading…
Reference in New Issue