[SelectionDAG] Legalize <1 x T> vector types for atomic load

llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h

@@ -874,6 +874,7 @@ class LLVM_LIBRARY_VISIBILITY DAGTypeLegalizer {
   SDValue ScalarizeVecRes_UnaryOpWithExtraInput(SDNode *N);
   SDValue ScalarizeVecRes_INSERT_VECTOR_ELT(SDNode *N);
   SDValue ScalarizeVecRes_LOAD(LoadSDNode *N);
+  SDValue ScalarizeVecRes_ATOMIC_LOAD(AtomicSDNode *N);
   SDValue ScalarizeVecRes_SCALAR_TO_VECTOR(SDNode *N);
   SDValue ScalarizeVecRes_VSELECT(SDNode *N);
   SDValue ScalarizeVecRes_SELECT(SDNode *N);

llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp

@@ -64,6 +64,9 @@ void DAGTypeLegalizer::ScalarizeVectorResult(SDNode *N, unsigned ResNo) {
     R = ScalarizeVecRes_UnaryOpWithExtraInput(N);
     break;
   case ISD::INSERT_VECTOR_ELT: R = ScalarizeVecRes_INSERT_VECTOR_ELT(N); break;
+  case ISD::ATOMIC_LOAD:
+    R = ScalarizeVecRes_ATOMIC_LOAD(cast<AtomicSDNode>(N));
+    break;
   case ISD::LOAD:           R = ScalarizeVecRes_LOAD(cast<LoadSDNode>(N));break;
   case ISD::SCALAR_TO_VECTOR:  R = ScalarizeVecRes_SCALAR_TO_VECTOR(N); break;
   case ISD::SIGN_EXTEND_INREG: R = ScalarizeVecRes_InregOp(N); break;
@@ -458,6 +461,18 @@ SDValue DAGTypeLegalizer::ScalarizeVecRes_INSERT_VECTOR_ELT(SDNode *N) {
   return Op;
 }
 
+SDValue DAGTypeLegalizer::ScalarizeVecRes_ATOMIC_LOAD(AtomicSDNode *N) {
+  SDValue Result = DAG.getAtomicLoad(
+      ISD::NON_EXTLOAD, SDLoc(N), N->getMemoryVT().getVectorElementType(),
+      N->getValueType(0).getVectorElementType(), N->getChain(), N->getBasePtr(),
+      N->getMemOperand());
+
+  // Legalize the chain result - switch anything that used the old chain to
+  // use the new one.
+  ReplaceValueWith(SDValue(N, 1), Result.getValue(1));
+  return Result;
+}
+
 SDValue DAGTypeLegalizer::ScalarizeVecRes_LOAD(LoadSDNode *N) {
   assert(N->isUnindexed() && "Indexed vector load?");
 

llvm/test/CodeGen/X86/atomic-load-store.ll

@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-apple-macosx10.7.0 -verify-machineinstrs | FileCheck %s
-; RUN: llc < %s -mtriple=x86_64-apple-macosx10.7.0 -verify-machineinstrs -O0 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-apple-macosx10.7.0 -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,CHECK3
+; RUN: llc < %s -mtriple=x86_64-apple-macosx10.7.0 -verify-machineinstrs -O0 | FileCheck %s --check-prefixes=CHECK,CHECK0
 
 define void @test1(ptr %ptr, i32 %val1) {
 ; CHECK-LABEL: test1:
@@ -28,3 +28,120 @@ define i32 @test3(ptr %ptr) {
   %val = load atomic i32, ptr %ptr seq_cst, align 4
   ret i32 %val
 }
+
+define <1 x i32> @atomic_vec1_i32(ptr %x) {
+; CHECK-LABEL: atomic_vec1_i32:
+; CHECK:       ## %bb.0:
+; CHECK-NEXT:    movl (%rdi), %eax
+; CHECK-NEXT:    retq
+  %ret = load atomic <1 x i32>, ptr %x acquire, align 4
+  ret <1 x i32> %ret
+}
+
+define <1 x i8> @atomic_vec1_i8(ptr %x) {
+; CHECK3-LABEL: atomic_vec1_i8:
+; CHECK3:       ## %bb.0:
+; CHECK3-NEXT:    movzbl (%rdi), %eax
+; CHECK3-NEXT:    retq
+;
+; CHECK0-LABEL: atomic_vec1_i8:
+; CHECK0:       ## %bb.0:
+; CHECK0-NEXT:    movb (%rdi), %al
+; CHECK0-NEXT:    retq
+  %ret = load atomic <1 x i8>, ptr %x acquire, align 1
+  ret <1 x i8> %ret
+}
+
+define <1 x i16> @atomic_vec1_i16(ptr %x) {
+; CHECK3-LABEL: atomic_vec1_i16:
+; CHECK3:       ## %bb.0:
+; CHECK3-NEXT:    movzwl (%rdi), %eax
+; CHECK3-NEXT:    retq
+;
+; CHECK0-LABEL: atomic_vec1_i16:
+; CHECK0:       ## %bb.0:
+; CHECK0-NEXT:    movw (%rdi), %ax
+; CHECK0-NEXT:    retq
+  %ret = load atomic <1 x i16>, ptr %x acquire, align 2
+  ret <1 x i16> %ret
+}
+
+define <1 x i32> @atomic_vec1_i8_zext(ptr %x) {
+; CHECK3-LABEL: atomic_vec1_i8_zext:
+; CHECK3:       ## %bb.0:
+; CHECK3-NEXT:    movzbl (%rdi), %eax
+; CHECK3-NEXT:    movzbl %al, %eax
+; CHECK3-NEXT:    retq
+;
+; CHECK0-LABEL: atomic_vec1_i8_zext:
+; CHECK0:       ## %bb.0:
+; CHECK0-NEXT:    movb (%rdi), %al
+; CHECK0-NEXT:    movzbl %al, %eax
+; CHECK0-NEXT:    retq
+  %ret = load atomic <1 x i8>, ptr %x acquire, align 1
+  %zret = zext <1 x i8> %ret to <1 x i32>
+  ret <1 x i32> %zret
+}
+
+define <1 x i64> @atomic_vec1_i16_sext(ptr %x) {
+; CHECK3-LABEL: atomic_vec1_i16_sext:
+; CHECK3:       ## %bb.0:
+; CHECK3-NEXT:    movzwl (%rdi), %eax
+; CHECK3-NEXT:    movswq %ax, %rax
+; CHECK3-NEXT:    retq
+;
+; CHECK0-LABEL: atomic_vec1_i16_sext:
+; CHECK0:       ## %bb.0:
+; CHECK0-NEXT:    movw (%rdi), %ax
+; CHECK0-NEXT:    movswq %ax, %rax
+; CHECK0-NEXT:    retq
+  %ret = load atomic <1 x i16>, ptr %x acquire, align 2
+  %sret = sext <1 x i16> %ret to <1 x i64>
+  ret <1 x i64> %sret
+}
+
+define <1 x ptr addrspace(270)> @atomic_vec1_ptr270(ptr %x) {
+; CHECK-LABEL: atomic_vec1_ptr270:
+; CHECK:       ## %bb.0:
+; CHECK-NEXT:    movl (%rdi), %eax
+; CHECK-NEXT:    retq
+  %ret = load atomic <1 x ptr addrspace(270)>, ptr %x acquire, align 4
+  ret <1 x ptr addrspace(270)> %ret
+}
+
+define <1 x bfloat> @atomic_vec1_bfloat(ptr %x) {
+; CHECK3-LABEL: atomic_vec1_bfloat:
+; CHECK3:       ## %bb.0:
+; CHECK3-NEXT:    movzwl (%rdi), %eax
+; CHECK3-NEXT:    pinsrw $0, %eax, %xmm0
+; CHECK3-NEXT:    retq
+;
+; CHECK0-LABEL: atomic_vec1_bfloat:
+; CHECK0:       ## %bb.0:
+; CHECK0-NEXT:    movw (%rdi), %cx
+; CHECK0-NEXT:    ## implicit-def: $eax
+; CHECK0-NEXT:    movw %cx, %ax
+; CHECK0-NEXT:    ## implicit-def: $xmm0
+; CHECK0-NEXT:    pinsrw $0, %eax, %xmm0
+; CHECK0-NEXT:    retq
+  %ret = load atomic <1 x bfloat>, ptr %x acquire, align 2
+  ret <1 x bfloat> %ret
+}
+
+define <1 x ptr> @atomic_vec1_ptr_align(ptr %x) nounwind {
+; CHECK-LABEL: atomic_vec1_ptr_align:
+; CHECK:       ## %bb.0:
+; CHECK-NEXT:    movq (%rdi), %rax
+; CHECK-NEXT:    retq
+  %ret = load atomic <1 x ptr>, ptr %x acquire, align 8
+  ret <1 x ptr> %ret
+}
+
+define <1 x i64> @atomic_vec1_i64_align(ptr %x) nounwind {
+; CHECK-LABEL: atomic_vec1_i64_align:
+; CHECK:       ## %bb.0:
+; CHECK-NEXT:    movq (%rdi), %rax
+; CHECK-NEXT:    retq
+  %ret = load atomic <1 x i64>, ptr %x acquire, align 8
+  ret <1 x i64> %ret
+}