http://llvm.org/bugs/show_bug.cgi?id=17582
Bug ID: 17582
Summary: inefficient local dynamic code on x86_64
Product: libraries
Version: trunk
Hardware: PC
OS: Linux
Status: NEW
Severity: normal
Priority: P
Component: Backend: X86
Assignee: [email protected]
Reporter: [email protected]
CC: [email protected]
Classification: Unclassified
given
__attribute__((visibility("hidden"))) __thread int obj1;
__attribute__((visibility("hidden"))) __thread int obj2;
void f(int, int);
void test() {
f(((int)&obj1) > 0, ((int)&obj2) > 0);
}
clang correctly selects the local dynamic model (just one call to
__tls_get_addr), but the code is
leaq obj1@TLSLD(%rip), %rdi
callq __tls_get_addr@PLT
movq %rax, %rcx
movq $obj1@DTPOFF, %rdi
addl %ecx, %edi
movq $obj2@DTPOFF, %rsi
addl %eax, %esi
the movq %rax, %rcx seems pointless. We can just add from %eax directly.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
LLVMbugs mailing list
[email protected]
http://lists.cs.uiuc.edu/mailman/listinfo/llvmbugs
