[GlobalISel] Fix a bug in LegalizeRuleSet::clampMaxNumElements

Volkan Keles · Volkan Keles · commit 0a8dc9eb0fe0 · 2018-11-01T19:01:53.000Z
Summary: This function was causing a crash when `MaxElements == 1` because it was trying to create a single element vector type. Reviewers: dsanders, aemerson, aditya_nandakumar Reviewed By: dsanders Subscribers: rovka, kristof.beyls, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D53734 llvm-svn: 345875
diff --git a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerInfo.h b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerInfo.h
@@ -693,6 +693,8 @@ class LegalizeRuleSet {
         },
         [=](const LegalityQuery &Query) {
           LLT VecTy = Query.Types[TypeIdx];
+          if (MaxElements == 1)
+            return std::make_pair(TypeIdx, VecTy.getElementType());
           return std::make_pair(
               TypeIdx, LLT::vector(MaxElements, VecTy.getScalarSizeInBits()));
         });
diff --git a/llvm/lib/Target/AArch64/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/AArch64LegalizerInfo.cpp
@@ -169,7 +169,8 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST) {
       .lowerIf([=](const LegalityQuery &Query) {
         return Query.Types[0].getSizeInBits() != Query.MMODescrs[0].SizeInBits;
       })
-      .clampNumElements(0, v2s32, v2s32);
+      .clampNumElements(0, v2s32, v2s32)
+      .clampMaxNumElements(0, s64, 1);
 
   getActionDefinitionsBuilder(G_STORE)
       .legalForTypesWithMemSize({{s8, p0, 8},
@@ -187,7 +188,8 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST) {
         return Query.Types[0].isScalar() &&
                Query.Types[0].getSizeInBits() != Query.MMODescrs[0].SizeInBits;
       })
-      .clampNumElements(0, v2s32, v2s32);
+      .clampNumElements(0, v2s32, v2s32)
+      .clampMaxNumElements(0, s64, 1);
 
   // Constants
   getActionDefinitionsBuilder(G_CONSTANT)
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-load-fewerElts.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-load-fewerElts.mir
@@ -0,0 +1,39 @@
+# RUN: llc -march=aarch64 -o - -run-pass=legalizer -global-isel-abort=0 -debug-only=legalizer 2>&1 %s | FileCheck %s
+# REQUIRES: asserts
+
+# CHECK: Legalize Machine IR for: load_v4s32
+# CHECK-NEXT: %{{[0-9]+}}:_(<4 x s32>) = G_LOAD %{{[0-9]+}}:_(p0)
+# CHECK-NEXT: Reduce number of elements
+---
+name:            load_v4s32
+legalized:       false
+tracksRegLiveness: true
+body:             |
+  bb.1:
+    liveins: $x0
+
+    %0:_(p0) = COPY $x0
+    %1:_(<4 x s32>) = G_LOAD %0(p0) :: (load 16, align 4)
+    %2:_(s32), %3:_(s32), %4:_(s32), %5:_(s32) = G_UNMERGE_VALUES %1(<4 x s32>)
+    $w0 = COPY %5(s32)
+
+...
+
+# Make sure we are able to scalarize v2s64.
+# CHECK: Legalize Machine IR for: load_v2s64
+# CHECK-NEXT: %{{[0-9]+}}:_(<2 x s64>) = G_LOAD %{{[0-9]+}}:_(p0)
+# CHECK-NEXT: Reduce number of elements
+---
+name:            load_v2s64
+legalized:       false
+tracksRegLiveness: true
+body:             |
+  bb.1:
+    liveins: $x0
+
+    %0:_(p0) = COPY $x0
+    %1:_(<2 x s64>) = G_LOAD %0(p0) :: (load 16)
+    %2:_(s64), %3:_(s64) = G_UNMERGE_VALUES %1(<2 x s64>)
+    $x0 = COPY %3(s64)
+
+...
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-load-v4s32.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-load-v4s32.mir
