[PATCH] D26633: AMDGPU/GCN: Exit early in hazard recognizer if there is no vreg argument
Jan Vesely via llvm-commits
llvm-commits at lists.llvm.org
Tue Nov 15 16:05:08 PST 2016
This revision was automatically updated to reflect the committed changes.
Closed by commit rL287056: AMDGPU/GCN: Exit early in hazard recognizer if there is no vreg argument (authored by jvesely).
Changed prior to commit:
https://reviews.llvm.org/D26633?vs=77932&id=78094#toc
Repository:
rL LLVM
https://reviews.llvm.org/D26633
Files:
llvm/trunk/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.wbinvl1.vol.ll
Index: llvm/trunk/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
+++ llvm/trunk/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
@@ -400,6 +400,10 @@
VDataRCID = Desc.OpInfo[VDataIdx].RegClass;
if (TII->isMUBUF(MI) || TII->isMTBUF(MI)) {
+ // There is no hazard if the instruction does not use vector regs
+ // (like wbinvl1)
+ if (VDataIdx == -1)
+ return -1;
// For MUBUF/MTBUF instructions this hazard only exists if the
// instruction is not using a register in the soffset field.
const MachineOperand *SOffset =
Index: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.wbinvl1.vol.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.wbinvl1.vol.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.wbinvl1.vol.ll
@@ -7,9 +7,11 @@
; GCN-NEXT: ; BB#0:
; CI-NEXT: buffer_wbinvl1_vol ; encoding: [0x00,0x00,0xc0,0xe1,0x00,0x00,0x00,0x00]
; VI-NEXT: buffer_wbinvl1_vol ; encoding: [0x00,0x00,0xfc,0xe0,0x00,0x00,0x00,0x00]
-; GCN-NEXT: s_endpgm
+; GCN: s_endpgm
define void @test_buffer_wbinvl1_vol() #0 {
call void @llvm.amdgcn.buffer.wbinvl1.vol()
+; This used to crash in hazard recognizer
+ store i8 0, i8 addrspace(1)* undef, align 1
ret void
}
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D26633.78094.patch
Type: text/x-patch
Size: 1393 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20161116/6a3ca8a6/attachment.bin>
More information about the llvm-commits
mailing list