[PATCH] D56002: [AMDGPU] Fix a weird WWM intrinsic issue.
Neil Henning via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Dec 21 07:08:30 PST 2018
sheredom created this revision.
sheredom added reviewers: nhaehnle, arsenm.
sheredom added a project: AMDGPU.
Herald added subscribers: llvm-commits, t-tye, tpr, dstuttard, yaxunl, wdng, jvesely, kzhuravl.
I found a really strange WWM issue through a very convoluted shader that essentially boils down to a bug in SIInstrInfo where canReadVGPR did not correctly identify that WWM is like a copy and can have a VGPR as its source.
Repository:
rL LLVM
https://reviews.llvm.org/D56002
Files:
lib/Target/AMDGPU/SIInstrInfo.cpp
test/CodeGen/AMDGPU/fix-wwm-vgpr-copy.ll
Index: test/CodeGen/AMDGPU/fix-wwm-vgpr-copy.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/fix-wwm-vgpr-copy.ll
@@ -0,0 +1,50 @@
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"
+target triple = "amdgcn--amdpal"
+
+declare i64 @llvm.amdgcn.icmp.i32(i32, i32, i32) #0
+declare i32 @llvm.amdgcn.set.inactive.i32(i32, i32) #0
+declare i32 @llvm.amdgcn.wwm.i32(i32) #1
+declare void @llvm.amdgcn.tbuffer.store.f32(float, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #2
+declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #2
+
+define amdgpu_hs void @foo(i32 inreg %arg, <4 x i32> inreg %buffer) {
+entry:
+ br label %work
+
+bb42:
+ br label %bb602
+
+bb602:
+ %tmp603 = phi i32 [ 0, %bb42 ], [ 1, %work ]
+ %tmp607 = icmp eq i32 %tmp603, %tmp1196
+ br i1 %tmp607, label %bb49, label %bb54
+
+bb49:
+ tail call void @llvm.amdgcn.tbuffer.store.f32(float 1.000000e+00, <4 x i32> %buffer, i32 0, i32 1, i32 1, i32 4, i32 4, i32 7, i1 true, i1 false) #7
+ ret void
+
+bb54:
+ ret void
+
+work:
+; GCN: s_not_b64 exec, exec
+; GCN: v_mov_b32_e32 v[[tmp1189:[0-9]+]], 1
+; GCN: s_not_b64 exec, exec
+ %tmp1189 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 4, i32 1)
+
+; GCN: s_or_saveexec_b64 s{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]{{\]}}, -1
+; GCN: v_lshlrev_b32_e32 v[[tmp1191:[0-9]+]], 2, v[[tmp1189]]
+ %tmp1191 = mul i32 %tmp1189, 4
+
+; GCN: s_mov_b64 exec, s{{\[}}[[LO]]:[[HI]]{{\]}}
+ %tmp1196 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp1191)
+
+ %tmp34 = icmp eq i32 %arg, 0
+ br i1 %tmp34, label %bb602, label %bb42
+}
+
+attributes #0 = { convergent nounwind readnone }
+attributes #1 = { nounwind readnone speculatable }
+attributes #2 = { nounwind writeonly }
Index: lib/Target/AMDGPU/SIInstrInfo.cpp
===================================================================
--- lib/Target/AMDGPU/SIInstrInfo.cpp
+++ lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -3230,6 +3230,8 @@
bool SIInstrInfo::canReadVGPR(const MachineInstr &MI, unsigned OpNo) const {
switch (MI.getOpcode()) {
case AMDGPU::COPY:
+ case AMDGPU::WQM:
+ case AMDGPU::WWM:
case AMDGPU::REG_SEQUENCE:
case AMDGPU::PHI:
case AMDGPU::INSERT_SUBREG:
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D56002.179282.patch
Type: text/x-patch
Size: 2480 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20181221/13284e36/attachment.bin>
More information about the llvm-commits
mailing list