[llvm] 2deb10c - [AArch64][SVE] Fix crash for DestructiveBinaryComm zero merging

[via llvm-commits]

Author: zhongyunde
Date: 2023-01-17T20:45:59+08:00
New Revision: 2deb10c1084240f27bdd235fa26a7b001186847f

URL: https://github.com/llvm/llvm-project/commit/2deb10c1084240f27bdd235fa26a7b001186847f
DIFF: https://github.com/llvm/llvm-project/commit/2deb10c1084240f27bdd235fa26a7b001186847f.diff

LOG: [AArch64][SVE] Fix crash for DestructiveBinaryComm zero merging

This fix is similar to D124325, and I find the DestructiveBinaryComm
operation type also may be allocated same register, so insert the LSL.

      movprfx       z0.s, p0/z, z0.s
      lsl z0.b, p0/m, z0.b, #0
      fmul z0.s, p0/m, z0.s, z0.s

Reviewed By: paulwalker-arm

Differential Revision: https://reviews.llvm.org/D141471

Added: 
    llvm/test/CodeGen/AArch64/sve-intrinsics-int-binaryComm-merging.mir

Modified: 
    llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp b/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
index e903c52fead72..eeaa8edb7cc56 100644
--- a/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
@@ -558,7 +558,8 @@ bool AArch64ExpandPseudo::expand_DestructiveOp(
   if (FalseZero) {
     // If we cannot prefix the requested instruction we'll instead emit a
     // prefixed_zeroing_mov for DestructiveBinary.
-    assert((DOPRegIsUnique || AArch64::DestructiveBinary == DType) &&
+    assert((DOPRegIsUnique || ((DType == AArch64::DestructiveBinary) ||
+                               (DType = AArch64::DestructiveBinaryComm))) &&
            "The destructive operand should be unique");
     assert(ElementSize != AArch64::ElementSizeNone &&
            "This instruction is unpredicated");
@@ -575,7 +576,9 @@ bool AArch64ExpandPseudo::expand_DestructiveOp(
     // Create the additional LSL to zero the lanes when the DstReg is not
     // unique. Zeros the lanes in z0 that aren't active in p0 with sequence
     // movprfx z0.b, p0/z, z0.b; lsl z0.b, p0/m, z0.b, #0;
-    if (DType == AArch64::DestructiveBinary && !DOPRegIsUnique) {
+    if (((DType == AArch64::DestructiveBinary) ||
+         (DType == AArch64::DestructiveBinaryComm)) &&
+        !DOPRegIsUnique) {
       BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(LSLZero))
           .addReg(DstReg, RegState::Define)
           .add(MI.getOperand(PredIdx))

diff  --git a/llvm/test/CodeGen/AArch64/sve-intrinsics-int-binaryComm-merging.mir b/llvm/test/CodeGen/AArch64/sve-intrinsics-int-binaryComm-merging.mir
new file mode 100644
index 0000000000000..c5ee307d67261
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-intrinsics-int-binaryComm-merging.mir
@@ -0,0 +1,39 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=aarch64 -mattr=+sve -mattr=+use-experimental-zeroing-pseudos -run-pass=aarch64-expand-pseudo %s -o - | FileCheck %s
+
+# Should create an additional LSL to zero the lanes as the DstReg is not unique
+
+--- |
+  define <vscale x 4 x float> @fmul_float_zero(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a){
+    %a_z = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> zeroinitializer
+    %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a_z, <vscale x 4 x float> %a_z)
+    ret <vscale x 4 x float> %out
+  }
+
+  declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
+...
+---
+name:            fmul_float_zero
+alignment:       4
+tracksRegLiveness: true
+tracksDebugUserValues: true
+registers:       []
+liveins:
+  - { reg: '$p0', virtual-reg: '' }
+  - { reg: '$z0', virtual-reg: '' }
+body:             |
+  bb.0 (%ir-block.0):
+    liveins: $p0, $z0
+
+    ; CHECK-LABEL: name: fmul_float_zero
+    ; CHECK: liveins: $p0, $z0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: BUNDLE implicit-def $z0, implicit-def $q0, implicit-def $d0, implicit-def $s0, implicit-def $h0, implicit-def $b0, implicit-def $z0_hi, implicit $p0, implicit $z0 {
+    ; CHECK-NEXT:   $z0 = MOVPRFX_ZPzZ_S $p0, $z0
+    ; CHECK-NEXT:   $z0 = LSL_ZPmI_S renamable $p0, internal $z0, 0
+    ; CHECK-NEXT:   $z0 = FMUL_ZPmZ_S renamable $p0, internal killed $z0, internal killed renamable $z0
+    ; CHECK-NEXT: }
+    ; CHECK-NEXT: RET undef $lr, implicit $z0
+    renamable $z0 = nnan ninf nsz arcp contract afn reassoc FMUL_ZPZZ_ZERO_S renamable $p0, killed renamable $z0, renamable $z0
+    RET_ReallyLR implicit $z0
+...