mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 19:52:54 +01:00
d382d6f3fc
OpenCL 2.0 introduces the notion of memory scopes in atomic operations to
global and local memory. These scopes restrict how synchronization is
achieved, which can result in improved performance.
This change extends existing notion of synchronization scopes in LLVM to
support arbitrary scopes expressed as target-specific strings, in addition to
the already defined scopes (single thread, system).
The LLVM IR and MIR syntax for expressing synchronization scopes has changed
to use *syncscope("<scope>")*, where <scope> can be "singlethread" (this
replaces *singlethread* keyword), or a target-specific name. As before, if
the scope is not specified, it defaults to CrossThread/System scope.
Implementation details:
- Mapping from synchronization scope name/string to synchronization scope id
is stored in LLVM context;
- CrossThread/System and SingleThread scopes are pre-defined to efficiently
check for known scopes without comparing strings;
- Synchronization scope names are stored in SYNC_SCOPE_NAMES_BLOCK in
the bitcode.
Differential Revision: https://reviews.llvm.org/D21723
llvm-svn: 307722
42 lines
2.2 KiB
LLVM
42 lines
2.2 KiB
LLVM
; RUN: opt < %s | opt -S | FileCheck %s
|
|
; RUN: verify-uselistorder %s
|
|
; Basic smoke test for atomic operations.
|
|
|
|
define void @f(i32* %x) {
|
|
; CHECK: load atomic i32, i32* %x unordered, align 4
|
|
load atomic i32, i32* %x unordered, align 4
|
|
; CHECK: load atomic volatile i32, i32* %x syncscope("singlethread") acquire, align 4
|
|
load atomic volatile i32, i32* %x syncscope("singlethread") acquire, align 4
|
|
; CHECK: load atomic volatile i32, i32* %x syncscope("agent") acquire, align 4
|
|
load atomic volatile i32, i32* %x syncscope("agent") acquire, align 4
|
|
; CHECK: store atomic i32 3, i32* %x release, align 4
|
|
store atomic i32 3, i32* %x release, align 4
|
|
; CHECK: store atomic volatile i32 3, i32* %x syncscope("singlethread") monotonic, align 4
|
|
store atomic volatile i32 3, i32* %x syncscope("singlethread") monotonic, align 4
|
|
; CHECK: store atomic volatile i32 3, i32* %x syncscope("workgroup") monotonic, align 4
|
|
store atomic volatile i32 3, i32* %x syncscope("workgroup") monotonic, align 4
|
|
; CHECK: cmpxchg i32* %x, i32 1, i32 0 syncscope("singlethread") monotonic monotonic
|
|
cmpxchg i32* %x, i32 1, i32 0 syncscope("singlethread") monotonic monotonic
|
|
; CHECK: cmpxchg i32* %x, i32 1, i32 0 syncscope("workitem") monotonic monotonic
|
|
cmpxchg i32* %x, i32 1, i32 0 syncscope("workitem") monotonic monotonic
|
|
; CHECK: cmpxchg volatile i32* %x, i32 0, i32 1 acq_rel acquire
|
|
cmpxchg volatile i32* %x, i32 0, i32 1 acq_rel acquire
|
|
; CHECK: cmpxchg i32* %x, i32 42, i32 0 acq_rel monotonic
|
|
cmpxchg i32* %x, i32 42, i32 0 acq_rel monotonic
|
|
; CHECK: cmpxchg weak i32* %x, i32 13, i32 0 seq_cst monotonic
|
|
cmpxchg weak i32* %x, i32 13, i32 0 seq_cst monotonic
|
|
; CHECK: atomicrmw add i32* %x, i32 10 seq_cst
|
|
atomicrmw add i32* %x, i32 10 seq_cst
|
|
; CHECK: atomicrmw volatile xchg i32* %x, i32 10 monotonic
|
|
atomicrmw volatile xchg i32* %x, i32 10 monotonic
|
|
; CHECK: atomicrmw volatile xchg i32* %x, i32 10 syncscope("agent") monotonic
|
|
atomicrmw volatile xchg i32* %x, i32 10 syncscope("agent") monotonic
|
|
; CHECK: fence syncscope("singlethread") release
|
|
fence syncscope("singlethread") release
|
|
; CHECK: fence seq_cst
|
|
fence seq_cst
|
|
; CHECK: fence syncscope("device") seq_cst
|
|
fence syncscope("device") seq_cst
|
|
ret void
|
|
}
|