[llvm] c98644c - [X86] Fix a codegen crash in getSetCCResultType

[via llvm-commits]

Author: Wang, Pengfei
Date: 2021-02-19T17:30:10+08:00
New Revision: c98644c2ece2f00da5e4510d6fbd07ef89263220

URL: https://github.com/llvm/llvm-project/commit/c98644c2ece2f00da5e4510d6fbd07ef89263220
DIFF: https://github.com/llvm/llvm-project/commit/c98644c2ece2f00da5e4510d6fbd07ef89263220.diff

LOG: [X86] Fix a codegen crash in getSetCCResultType

This patch fixes some crashes coming from
X86ISelLowering::getSetCCResultType, which would occasionally return
an EVT constructed from an invalid MVT, which has a null Type pointer.

This patch refers to D95434.

Differential Revision: https://reviews.llvm.org/D97036

Added: 
    llvm/test/CodeGen/X86/vec3-setcc-crash.ll

Modified: 
    llvm/lib/Target/X86/X86ISelLowering.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 501274dc471d..e5f454a251dd 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -2221,7 +2221,7 @@ EVT X86TargetLowering::getSetCCResultType(const DataLayout &DL,
 
     // If we got a 512-bit vector then we'll definitely have a vXi1 compare.
     if (LegalVT.getSimpleVT().is512BitVector())
-      return VT.changeVectorElementType(MVT::i1);
+      return EVT::getVectorVT(Context, MVT::i1, VT.getVectorElementCount());
 
     if (LegalVT.getSimpleVT().isVector() && Subtarget.hasVLX()) {
       // If we legalized to less than a 512-bit vector, then we will use a vXi1
@@ -2229,7 +2229,7 @@ EVT X86TargetLowering::getSetCCResultType(const DataLayout &DL,
       // vXi16/vXi8.
       MVT EltVT = LegalVT.getSimpleVT().getVectorElementType();
       if (Subtarget.hasBWI() || EltVT.getSizeInBits() >= 32)
-        return VT.changeVectorElementType(MVT::i1);
+        return EVT::getVectorVT(Context, MVT::i1, VT.getVectorElementCount());
     }
   }
 

diff  --git a/llvm/test/CodeGen/X86/vec3-setcc-crash.ll b/llvm/test/CodeGen/X86/vec3-setcc-crash.ll
new file mode 100644
index 000000000000..61c38c05969c
--- /dev/null
+++ b/llvm/test/CodeGen/X86/vec3-setcc-crash.ll
@@ -0,0 +1,31 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=X86
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=X64
+
+define void @vec3_setcc_crash(<3 x i32>* %in, <3 x i32>* %out) {
+; X86-LABEL: vec3_setcc_crash:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    vmovdqa (%ecx), %xmm0
+; X86-NEXT:    vptestnmd %xmm0, %xmm0, %k1
+; X86-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
+; X86-NEXT:    vpextrd $2, %xmm0, 8(%eax)
+; X86-NEXT:    vpextrd $1, %xmm0, 4(%eax)
+; X86-NEXT:    vmovd %xmm0, (%eax)
+; X86-NEXT:    retl
+;
+; X64-LABEL: vec3_setcc_crash:
+; X64:       # %bb.0:
+; X64-NEXT:    vmovdqa (%rdi), %xmm0
+; X64-NEXT:    vptestnmd %xmm0, %xmm0, %k1
+; X64-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
+; X64-NEXT:    vpextrd $2, %xmm0, 8(%rsi)
+; X64-NEXT:    vmovq %xmm0, (%rsi)
+; X64-NEXT:    retq
+  %a = load <3 x i32>, <3 x i32>* %in
+  %cmp = icmp eq <3 x i32> %a, zeroinitializer
+  %c = select <3 x i1> %cmp, <3 x i32> %a, <3 x i32> zeroinitializer
+  store <3 x i32> %c, <3 x i32>* %out
+  ret void
+}