Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Summary: I originally tried doing this specifically for X86 in the backend in D5091, but it was rather brittle and generally running too late to be general. Furthermore, other targets may want to implement similar optimizations. So I reimplemented it at the IR-level, fitting it into AtomicExpandPass as it interacts with that pass (which could not be cleanly done before at the backend level). This optimization relies on a new target hook, which is only used by X86 for now, as the correctness of the optimization on other targets remains an open question. If it is found correct on other targets, it should be trivial to enable for them. Details of the optimization are discussed in D5091. Test Plan: make check-all + a new test Reviewers: jfb Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D5422 llvm-svn: 218455
- Loading branch information
Robin Morisset
committed
Sep 25, 2014
1 parent
8cb2cae
commit 810739d
Showing
5 changed files
with
185 additions
and
6 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,56 @@ | ||
; RUN: llc < %s -march=x86-64 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=X64 | ||
; RUN: llc < %s -march=x86 -mattr=+sse2 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=X32 | ||
|
||
; On x86, an atomic rmw operation that does not modify the value in memory | ||
; (such as atomic add 0) can be replaced by an mfence followed by a mov. | ||
; This is explained (with the motivation for such an optimization) in | ||
; http://www.hpl.hp.com/techreports/2012/HPL-2012-68.pdf | ||
|
||
define i8 @add8(i8* %p) { | ||
; CHECK-LABEL: add8 | ||
; CHECK: mfence | ||
; CHECK: movb | ||
%1 = atomicrmw add i8* %p, i8 0 monotonic | ||
ret i8 %1 | ||
} | ||
|
||
define i16 @or16(i16* %p) { | ||
; CHECK-LABEL: or16 | ||
; CHECK: mfence | ||
; CHECK: movw | ||
%1 = atomicrmw or i16* %p, i16 0 acquire | ||
ret i16 %1 | ||
} | ||
|
||
define i32 @xor32(i32* %p) { | ||
; CHECK-LABEL: xor32 | ||
; CHECK: mfence | ||
; CHECK: movl | ||
%1 = atomicrmw xor i32* %p, i32 0 release | ||
ret i32 %1 | ||
} | ||
|
||
define i64 @sub64(i64* %p) { | ||
; CHECK-LABEL: sub64 | ||
; X64: mfence | ||
; X64: movq | ||
; X32-NOT: mfence | ||
%1 = atomicrmw sub i64* %p, i64 0 seq_cst | ||
ret i64 %1 | ||
} | ||
|
||
define i128 @or128(i128* %p) { | ||
; CHECK-LABEL: or128 | ||
; CHECK-NOT: mfence | ||
%1 = atomicrmw or i128* %p, i128 0 monotonic | ||
ret i128 %1 | ||
} | ||
|
||
; For 'and', the idempotent value is (-1) | ||
define i32 @and32 (i32* %p) { | ||
; CHECK-LABEL: and32 | ||
; CHECK: mfence | ||
; CHECK: movl | ||
%1 = atomicrmw and i32* %p, i32 -1 acq_rel | ||
ret i32 %1 | ||
} |