RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2024-11-27 21:50:40 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[NVPTX] Mark nvvm synchronizing intrinsics as convergent.

Browse Source 
Summary:
This is the attribute purpose-made for e.g. __syncthreads.  It appears
that NoDuplicate may not be sufficient to prevent Sink from touching a
call to __syncthreads.

Reviewers: jingyue, hfinkel

Subscribers: llvm-commits, jholewinski, jhen, rnk, tra, majnemer

Differential Revision: http://reviews.llvm.org/D16941

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@260005 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Justin Lebar 2016-02-06 19:32:44 +00:00
parent d14beda7f7
commit d98b8105e7
2 changed files with 11 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
include/llvm/IR/IntrinsicsNVVM.td
View File

@ -729,16 +729,20 @@ def llvm_anyi64ptr_ty : LLVMAnyPointerType<llvm_i64_ty>; // (space)i64*
[IntrReadWriteArgMem, NoCapture<0>]>;
// Bar.Sync
//
// TODO: Remove NoDuplicate here after fixing up LLVM to handle convergent
// properly. See discussion in http://reviews.llvm.org/D16941 and
// http://reviews.llvm.org/D12246.
def int_cuda_syncthreads : GCCBuiltin<"__syncthreads">,
Intrinsic<[], [], [IntrNoDuplicate]>;
Intrinsic<[], [], [IntrNoDuplicate, IntrConvergent]>;
def int_nvvm_barrier0 : GCCBuiltin<"__nvvm_bar0">,
Intrinsic<[], [], [IntrNoDuplicate]>;
Intrinsic<[], [], [IntrNoDuplicate, IntrConvergent]>;
def int_nvvm_barrier0_popc : GCCBuiltin<"__nvvm_bar0_popc">,
Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoDuplicate]>;
Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoDuplicate, IntrConvergent]>;
def int_nvvm_barrier0_and : GCCBuiltin<"__nvvm_bar0_and">,
Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoDuplicate]>;
Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoDuplicate, IntrConvergent]>;
def int_nvvm_barrier0_or : GCCBuiltin<"__nvvm_bar0_or">,
Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoDuplicate]>;
Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoDuplicate, IntrConvergent]>;
// Membar
def int_nvvm_membar_cta : GCCBuiltin<"__nvvm_membar_cta">,

4
test/Feature/intrinsic-noduplicate.ll
View File

@ -1,9 +1,9 @@
; RUN: llvm-as < %s | llvm-dis | FileCheck %s
; Make sure LLVM knows about the noduplicate attribute on the
; Make sure LLVM knows about the convergent and noduplicate attributes on the
; llvm.cuda.syncthreads intrinsic.
declare void @llvm.cuda.syncthreads()
; CHECK: declare void @llvm.cuda.syncthreads() #[[ATTRNUM:[0-9]+]]
; CHECK: attributes #[[ATTRNUM]] = { noduplicate nounwind }
; CHECK: attributes #[[ATTRNUM]] = { convergent noduplicate nounwind }