http://llvm.org/bugs/show_bug.cgi?id=17109
Bug ID: 17109
Summary: generate more efficient code for logical and operation
Product: libraries
Version: trunk
Hardware: PC
OS: All
Status: NEW
Severity: normal
Priority: P
Component: Backend: X86
Assignee: [email protected]
Reporter: [email protected]
CC: [email protected]
Classification: Unclassified
$ ./clang -v
clang version 3.4 (trunk 189776)
Target: x86_64-apple-darwin11.4.2
Thread model: posix
$ cat and.c
#include <stdbool.h>
bool and(unsigned int x, unsigned int y) {
return (x != 0 && y != 0);
}
$ ./clang -S -O3 -fomit-frame-pointer and.c -o /dev/stdout
.section __TEXT,__text,regular,pure_instructions
.globl _and
.align 4, 0x90
_and: ## @and
.cfi_startproc
## BB#0: ## %entry
testl %edi, %edi
setne %cl
testl %esi, %esi
setne %al
andb %cl, %al
ret
...
I think this codegen can be improved in size and speed by taking advantage of
the fact that the x86 'test' instruction does a bitwise 'and' operation.
Something like this:
testl %edi, %esi
setne %al
ret
--
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
