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

RegisterCoalescer: Shrink main range after shrinking subranges 

If the subregister uses were dead, this would leave the main range
segment pointing to a deleted instruction.

Not sure if this should try to avoid shrinking if we know we don't
have dead components.
This commit is contained in:
Matt Arsenault 2022-06-06 19:34:36 -04:00
parent b25902736c
commit a4834ad068
3 changed files with 35 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/CodeGen/RegisterCoalescer.cpp
View File

@ -2103,6 +2103,7 @@ bool RegisterCoalescer::joinCopy(MachineInstr *CopyMI, bool &Again) {
LLVM_DEBUG(dbgs() << "Shrink LaneUses (Lane " << PrintLaneMask(S.LaneMask)
<< ")\n");
LIS->shrinkToUses(S, LI.reg());
ShrinkMainRange = true;
}
LI.removeEmptySubRanges();
}

33
llvm/test/CodeGen/AMDGPU/coalesce-into-dead-subreg-copies.mir Normal file
View File

@ -0,0 +1,33 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-coalescing -run-pass=simple-register-coalescing -o - %s | FileCheck %s
# Check that there's no "Live segment doesn't end at a valid
# instruction" failure after coalescing %0 into %2, which is
# ultimately a pair of dead copies.
---
name: coalesce_into_dead_subreg_copy
tracksRegLiveness: true
machineFunctionInfo:
isEntryFunction: true
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
stackPtrOffsetReg: '$sgpr32'
occupancy: 8
body: |
; CHECK-LABEL: name: coalesce_into_dead_subreg_copy
; CHECK: bb.0:
; CHECK-NEXT: successors: %bb.1(0x80000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: dead %2:sreg_64_xexec = S_LOAD_DWORDX2_IMM undef %1:sgpr_64, 24, 0 :: (dereferenceable invariant load (s64), addrspace 4)
; CHECK-NEXT: S_BRANCH %bb.1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
bb.0:
%0:sreg_64_xexec = S_LOAD_DWORDX2_IMM undef %1:sgpr_64, 24, 0 :: (dereferenceable invariant load (s64), addrspace 4)
undef %2.sub0:sreg_64 = COPY %0.sub0:sreg_64_xexec
%2.sub1:sreg_64 = COPY killed %0.sub1:sreg_64_xexec
S_BRANCH %bb.1
bb.1:
...

2
llvm/test/CodeGen/AMDGPU/loop-live-out-copy-undef-subrange.ll
View File

@ -10,7 +10,7 @@ define <3 x float> @liveout_undef_subrange(<3 x float> %arg) {
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: v_add_f32_e32 v3, v2, v2
; CHECK-NEXT: v_add_f32_e32 v1, v1, v1
; CHECK-NEXT: ; kill: killed $vgpr1
; CHECK-NEXT: v_add_f32_e32 v0, v0, v0
; CHECK-NEXT: .LBB0_1: ; %bb1
; CHECK-NEXT: ; =>This Loop Header: Depth=1