return Subtarget.hasLZCNT();
}
+bool X86TargetLowering::canMergeStoresTo(unsigned AddressSpace, EVT MemVT,
+ const SelectionDAG &DAG) const {
+ // Do not merge to float value size (128 bytes) if no implicit
+ // float attribute is set.
+ bool NoFloat = DAG.getMachineFunction().getFunction()->hasFnAttribute(
+ Attribute::NoImplicitFloat);
+
+ if (NoFloat) {
+ unsigned MaxIntSize = Subtarget.is64Bit() ? 64 : 32;
+ return (MemVT.getSizeInBits() <= MaxIntSize);
+ }
+ return true;
+}
+
bool X86TargetLowering::isCtlzFast() const {
return Subtarget.hasFastLZCNT();
}
--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-apple-macosx10.13.0 | FileCheck %s --check-prefix=X86
+; RUN: llc < %s -mtriple=x86_64-apple-macosx10.13.0 | FileCheck %s --check-prefix=X64
+
+define void @thread_selfcounts() noimplicitfloat noredzone nounwind {
+; X86-LABEL: thread_selfcounts:
+; X86: ## BB#0: ## %entry
+; X86-NEXT: subl $44, %esp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl %ecx, {{[0-9]+}}(%esp)
+; X86-NEXT: movl %eax, (%esp)
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl %ecx, {{[0-9]+}}(%esp)
+; X86-NEXT: movl %eax, {{[0-9]+}}(%esp)
+; X86-NEXT: ## -- End function
+;
+; X64-LABEL: thread_selfcounts:
+; X64: ## BB#0: ## %entry
+; X64-NEXT: subq $40, %rsp
+; X64-NEXT: movq {{[0-9]+}}(%rsp), %rax
+; X64-NEXT: movq {{[0-9]+}}(%rsp), %rcx
+; X64-NEXT: movq %rax, (%rsp)
+; X64-NEXT: movq %rcx, {{[0-9]+}}(%rsp)
+; X64-NEXT: ## -- End function
+entry:
+ %counts = alloca [2 x i64], align 16
+ %thread_counts = alloca [3 x i64], align 16
+ %arraydecay = getelementptr inbounds [3 x i64], [3 x i64]* %thread_counts, i64 0, i64 0
+ %0 = load i64, i64* %arraydecay, align 16
+ %arrayidx3 = getelementptr inbounds [2 x i64], [2 x i64]* %counts, i64 0, i64 0
+ store i64 %0, i64* %arrayidx3, align 16
+ %arrayidx6 = getelementptr inbounds [3 x i64], [3 x i64]* %thread_counts, i64 0, i64 1
+ %1 = load i64, i64* %arrayidx6, align 8
+ %arrayidx10 = getelementptr inbounds [2 x i64], [2 x i64]* %counts, i64 0, i64 1
+ store i64 %1, i64* %arrayidx10, align 8
+ unreachable
+}
+