bb80d3e1d3
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
12 lines
431 B
LLVM
12 lines
431 B
LLVM
; RUN: llvm-link %S/Inputs/syncscope-1.ll %S/Inputs/syncscope-2.ll -S | FileCheck %s
|
|
|
|
; CHECK-LABEL: define void @syncscope_1
|
|
; CHECK: fence syncscope("agent") seq_cst
|
|
; CHECK: fence syncscope("workgroup") seq_cst
|
|
; CHECK: fence syncscope("wavefront") seq_cst
|
|
|
|
; CHECK-LABEL: define void @syncscope_2
|
|
; CHECK: fence syncscope("image") seq_cst
|
|
; CHECK: fence syncscope("agent") seq_cst
|
|
; CHECK: fence syncscope("workgroup") seq_cst
|