MCP: Fixed bug with dest overlapping copy source

Tim Renouf · trenouf · commit 07ebd741546e · 2019-11-12T08:18:11.000Z
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
diff --git a/llvm/lib/CodeGen/MachineCopyPropagation.cpp b/llvm/lib/CodeGen/MachineCopyPropagation.cpp
@@ -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);
diff --git a/llvm/test/CodeGen/AMDGPU/mcp-overlap-after-propagation.mir b/llvm/test/CodeGen/AMDGPU/mcp-overlap-after-propagation.mir
@@ -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
+
+...
