RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-06 03:08:43 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

AMDGPU: llvm.amdgcn.writelane is a source of divergence

Browse Source 
Summary:
Consider:

  %r = call i32 @llvm.amdgcn.writelane(i32 0, i32 1, i32 2)

This produces a value that is 0 on lane 1, and 2 everywhere else; i.e.,
it is divergent.

Reported-by: Marek Olsak <Marek.Olsak@amd.com>

Reviewers: arsenm, foad, mareko

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D74400
This commit is contained in:
Nicolai Hähnle 2020-02-11 14:40:00 +01:00
parent 7d05776a25
commit 894807cedd
2 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/Target/AMDGPU/AMDGPUSearchableTables.td
View File

@ -247,6 +247,7 @@ def : SourceOfDivergence<int_amdgcn_permlanex16>;
def : SourceOfDivergence<int_amdgcn_mov_dpp>;
def : SourceOfDivergence<int_amdgcn_mov_dpp8>;
def : SourceOfDivergence<int_amdgcn_update_dpp>;
def : SourceOfDivergence<int_amdgcn_writelane>;
def : SourceOfDivergence<int_amdgcn_mfma_f32_4x4x1f32>;
def : SourceOfDivergence<int_amdgcn_mfma_f32_4x4x1f32>;

8
test/Analysis/DivergenceAnalysis/AMDGPU/intrinsics.ll
View File

@ -42,12 +42,20 @@ define amdgpu_kernel void @mov_dpp8(i32 addrspace(1)* %out, i32 %in) #0 {
ret void
}
; CHECK: DIVERGENT: %tmp0 = call i32 @llvm.amdgcn.writelane(i32 0, i32 1, i32 2)
define amdgpu_kernel void @writelane(i32 addrspace(1)* %out) #0 {
%tmp0 = call i32 @llvm.amdgcn.writelane(i32 0, i32 1, i32 2)
store i32 %tmp0, i32 addrspace(1)* %out
ret void
}
declare i32 @llvm.amdgcn.ds.swizzle(i32, i32) #1
declare i32 @llvm.amdgcn.permlane16(i32, i32, i32, i32, i1, i1) #1
declare i32 @llvm.amdgcn.permlanex16(i32, i32, i32, i32, i1, i1) #1
declare i32 @llvm.amdgcn.mov.dpp.i32(i32, i32, i32, i32, i1) #1
declare i32 @llvm.amdgcn.mov.dpp8.i32(i32, i32) #1
declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32, i32, i32, i1) #1
declare i32 @llvm.amdgcn.writelane(i32, i32, i32) #1
attributes #0 = { nounwind convergent }
attributes #1 = { nounwind readnone convergent }