https://bugs.llvm.org/show_bug.cgi?id=46151
Bug ID: 46151
Summary: AArch64 missed optimization involving "or(frameindex,
n)"
Product: libraries
Version: trunk
Hardware: PC
OS: Windows NT
Status: NEW
Severity: enhancement
Priority: P
Component: Backend: AArch64
Assignee: unassignedb...@nondot.org
Reporter: efrie...@quicinc.com
CC: arnaud.degrandmai...@arm.com,
llvm-bugs@lists.llvm.org, smithp...@googlemail.com,
ties.st...@arm.com
Consider the following testcase:
int test(long n, void test2(int*)) {
int a[4] __attribute((aligned(16)));
test2(a);
return a[n & 3];
}
(Similar patterns can come up with variable-index extractelement.)
Currently, we generate something like the following:
mov x20, sp
and x8, x19, #0x3
bfi x20, x8, #2, #2
ldr w0, [x20]
If the "aligned" attribute is removed, we instead generate:
mov x20, sp
and x8, x19, #0x3
ldr w0, [x20, x8, lsl #2]
--
You are receiving this mail because:
You are on the CC list for the bug._______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
