maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

MCP: Fixed bug with dest overlapping copy source 

In MachineCopyPropagation, when propagating the source of a copy into
the operand of a later instruction, bail if a destination overlaps
(partly defines) the copy source. If the instruction where the
substitution is happening is also a copy, allowing the propagation
confuses the tracking mechanism.

Differential Revision: https://reviews.llvm.org/D69953

Change-Id: Ic570754f878f2d91a4a50a9bdcf96fbaa240726d
This commit is contained in:
Tim Renouf 2019-11-11 11:06:09 +00:00 committed by Tim Renouf
parent 22a535e91a
commit 07ebd74154
2 changed files with 36 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/CodeGen/MachineCopyPropagation.cpp
View File

@ -432,6 +432,15 @@ void MachineCopyPropagation::forwardUses(MachineInstr &MI) {
if (hasImplicitOverlap(MI, MOUse))
continue;
// Check that the instruction is not a copy that partially overwrites the
// original copy source that we are about to use. The tracker mechanism
// cannot cope with that.
if (MI.isCopy() && MI.modifiesRegister(CopySrcReg, TRI) &&
!MI.definesRegister(CopySrcReg)) {
LLVM_DEBUG(dbgs() << "MCP: Copy source overlap with dest in " << MI);
continue;
}
if (!DebugCounter::shouldExecute(FwdCounter)) {
LLVM_DEBUG(dbgs() << "MCP: Skipping forwarding due to debug counter:\n "
<< MI);

27
llvm/test/CodeGen/AMDGPU/mcp-overlap-after-propagation.mir Normal file
View File

@ -0,0 +1,27 @@
# RUN: llc -march=amdgcn -mcpu=gfx1010 %s -o - -run-pass machine-cp -verify-machineinstrs | FileCheck %s
#
# The MachineCopyPropagation bug being tested propagates s[60:67] into the copy
# into s[56:63], and then uses s[60:67] in the following
# IMAGE_SAMPLE_V3_V2_gfx10, even though it has just overwritten half of it.
# CHECK-LABEL: name: _amdgpu_ps_main
# CHECK-NOT: IMAGE_SAMPLE_V3_V2_gfx10 {{.*}} $sgpr60_sgpr61_sgpr62_sgpr63_sgpr64_sgpr65_sgpr66_sgpr67
# CHECK: IMAGE_SAMPLE_V3_V2_gfx10 {{.*}} $sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
---
name: _amdgpu_ps_main
body: |
bb.0:
successors:
liveins: $sgpr2, $sgpr3, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr5, $vgpr70, $vgpr71
renamable $sgpr8_sgpr9 = S_GETPC_B64
renamable $sgpr8 = COPY killed renamable $sgpr2
renamable $sgpr60_sgpr61_sgpr62_sgpr63_sgpr64_sgpr65_sgpr66_sgpr67 = S_LOAD_DWORDX8_IMM renamable $sgpr8_sgpr9, 144, 0, 0 :: (invariant load 32, align 16, addrspace 4)
renamable $sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95 = COPY killed renamable $sgpr60_sgpr61_sgpr62_sgpr63_sgpr64_sgpr65_sgpr66_sgpr67
renamable $vgpr4 = IMAGE_GET_LOD_V1_V2_gfx10 renamable $vgpr70_vgpr71, renamable $sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95, renamable $sgpr96_sgpr97_sgpr98_sgpr99, 2, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
renamable $sgpr56_sgpr57_sgpr58_sgpr59_sgpr60_sgpr61_sgpr62_sgpr63 = COPY killed renamable $sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
renamable $vgpr12_vgpr13_vgpr14 = IMAGE_SAMPLE_V3_V2_gfx10 renamable $vgpr70_vgpr71, renamable $sgpr56_sgpr57_sgpr58_sgpr59_sgpr60_sgpr61_sgpr62_sgpr63, renamable $sgpr96_sgpr97_sgpr98_sgpr99, 7, 1, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load 12, align 16)
S_ENDPGM 0
...