[PATCH] D59891: [PeepholeOpt] Don't stop simplifying copies on sequence of subregs

[Quentin Colombet via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL357095: [PeepholeOpt] Don't stop simplifying copies on sequence of subregs (authored by qcolombet, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D59891?vs=192469&id=192472#toc

Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D59891/new/

https://reviews.llvm.org/D59891

Files:
  llvm/trunk/lib/CodeGen/PeepholeOptimizer.cpp
  llvm/trunk/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir


Index: llvm/trunk/lib/CodeGen/PeepholeOptimizer.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/PeepholeOptimizer.cpp
+++ llvm/trunk/lib/CodeGen/PeepholeOptimizer.cpp
@@ -1900,13 +1900,8 @@
   // Def = REG_SEQUENCE v0, sub0, v1, sub1, ...
   // Check if one of the operand defines the subreg we are interested in.
   for (const RegSubRegPairAndIdx &RegSeqInput : RegSeqInputRegs) {
-    if (RegSeqInput.SubIdx == DefSubReg) {
-      if (RegSeqInput.SubReg)
-        // Bail if we have to compose sub registers.
-        return ValueTrackerResult();
-
+    if (RegSeqInput.SubIdx == DefSubReg)
       return ValueTrackerResult(RegSeqInput.Reg, RegSeqInput.SubReg);
-    }
   }
 
   // If the subreg we are tracking is super-defined by another subreg,
Index: llvm/trunk/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir
+++ llvm/trunk/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir
@@ -0,0 +1,34 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -march=amdgcn -run-pass peephole-opt -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
+
+# Check that when we jump through several subregisters in sequence of
+# reg_sequence we can still find a plain src for a copy.
+# In this specific test, we want %4 to read directly from %1 and
+# %5 from %0. These values come from the respective chains:
+# %4 -> %3.sub0 -> %2.sub1 -> %1
+# %5 -> %3.sub1 -> %2.sub0 -> %0
+#
+# We used to not simplify this because we were bailing when two
+# subreg indices were in the same chain (%3.subX and %2.subY)
+---
+name: reg_sequence_removal
+body:             |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GCN-LABEL: name: reg_sequence_removal
+    ; GCN: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+    ; GCN: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+    ; GCN: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+    ; GCN: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[REG_SEQUENCE]].sub1, %subreg.sub0, [[REG_SEQUENCE]].sub0, %subreg.sub1
+    ; GCN: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY1]]
+    ; GCN: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[COPY]]
+    ; GCN: KILL [[COPY3]], implicit [[COPY2]]
+    %0:vgpr_32 = COPY $vgpr0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1
+    %3:vreg_64 = REG_SEQUENCE %2.sub1, %subreg.sub0, %2.sub0, %subreg.sub1
+    %4:vgpr_32 = COPY %3.sub0
+    %5:vgpr_32 = COPY %3.sub1
+    KILL implicit %4, %5
+...


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D59891.192472.patch
Type: text/x-patch
Size: 2673 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190327/616968e7/attachment.bin>