Merging r339600:

------------------------------------------------------------------------
r339600 | scott.linder | 2018-08-13 20:44:21 +0200 (Mon, 13 Aug 2018) | 8 lines

[CodeGen] Fix assert in SelectionDAG::computeKnownBits

Fix SelectionDAG::computeKnownBits asserting when handling EXTRACT_SUBVECTOR
when zero extending the demanded elements mask if it is already as long as the
source vector.

Differential Revision: https://reviews.llvm.org/D49574

------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_70@339664 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 48e03c6..9e38e67 100644 (file)
--- a/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -2374,7 +2374,7 @@ void SelectionDAG::computeKnownBits(SDValue Op, KnownBits &Known,
     if (SubIdx && SubIdx->getAPIntValue().ule(NumSrcElts - NumElts)) {
       // Offset the demanded elts by the subvector index.
       uint64_t Idx = SubIdx->getZExtValue();
-      APInt DemandedSrc = DemandedElts.zext(NumSrcElts).shl(Idx);
+      APInt DemandedSrc = DemandedElts.zextOrSelf(NumSrcElts).shl(Idx);
       computeKnownBits(Src, Known, DemandedSrc, Depth + 1);
     } else {
       computeKnownBits(Src, Known, Depth + 1);
@@ -3533,7 +3533,7 @@ unsigned SelectionDAG::ComputeNumSignBits(SDValue Op, const APInt &DemandedElts,
     if (SubIdx && SubIdx->getAPIntValue().ule(NumSrcElts - NumElts)) {
       // Offset the demanded elts by the subvector index.
       uint64_t Idx = SubIdx->getZExtValue();
-      APInt DemandedSrc = DemandedElts.zext(NumSrcElts).shl(Idx);
+      APInt DemandedSrc = DemandedElts.zextOrSelf(NumSrcElts).shl(Idx);
       return ComputeNumSignBits(Src, DemandedSrc, Depth + 1);
     }
     return ComputeNumSignBits(Src, Depth + 1);

diff --git a/test/CodeGen/AMDGPU/extract-subvector-equal-length.ll b/test/CodeGen/AMDGPU/extract-subvector-equal-length.ll
new file mode 100644 (file)
index 0000000..6f7fb53
--- /dev/null
+++ b/test/CodeGen/AMDGPU/extract-subvector-equal-length.ll
@@ -0,0 +1,30 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -march=amdgcn -mtriple=amdgcn-- -verify-machineinstrs < %s | FileCheck %s
+
+; Test for ICE in SelectionDAG::computeKnownBits when visiting EXTRACT_SUBVECTOR
+; with DemandedElts already as wide as the source vector.
+
+define <3 x i32> @quux() #0 {
+; CHECK-LABEL: quux:
+; CHECK:       ; %bb.0: ; %bb
+; CHECK-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; CHECK-NEXT:    v_mov_b32_e32 v0, 0
+; CHECK-NEXT:    v_mov_b32_e32 v1, 1
+; CHECK-NEXT:    v_mov_b32_e32 v2, 1
+; CHECK-NEXT:    s_setpc_b64 s[30:31]
+bb:
+  %tmp = shufflevector <4 x i8> <i8 1, i8 2, i8 3, i8 4>, <4 x i8> undef, <3 x i32> <i32 0, i32 1, i32 2>
+  %tmp1 = extractelement <3 x i8> %tmp, i64 0
+  %tmp2 = zext i8 %tmp1 to i32
+  %tmp3 = insertelement <3 x i32> undef, i32 %tmp2, i32 0
+  %tmp4 = extractelement <3 x i8> %tmp, i64 1
+  %tmp5 = zext i8 %tmp4 to i32
+  %tmp6 = insertelement <3 x i32> %tmp3, i32 %tmp5, i32 1
+  %tmp7 = extractelement <3 x i8> %tmp, i64 2
+  %tmp8 = zext i8 %tmp7 to i32
+  %tmp9 = insertelement <3 x i32> %tmp6, i32 %tmp8, i32 2
+  %tmp10 = lshr <3 x i32> %tmp9, <i32 1, i32 1, i32 1>
+  ret <3 x i32> %tmp10
+}
+
+attributes #0 = { noinline optnone }