https://llvm.org/bugs/show_bug.cgi?id=24308
Bug ID: 24308
Summary: assembler: suboptimal encoding of memory operand
Product: libraries
Version: trunk
Hardware: PC
OS: Windows NT
Status: NEW
Severity: normal
Priority: P
Component: Backend: X86
Assignee: [email protected]
Reporter: [email protected]
CC: [email protected]
Classification: Unclassified
Given the following assembly input
vpaddd 16+0-4(%rdi, %rax), %xmm0, %xmm0
vpaddd 16+(0-4)(%rdi, %rax), %xmm0, %xmm0
vpaddd (16+0-4)(%rdi, %rax), %xmm0, %xmm0
vpaddd (16+0)-4(%rdi, %rax), %xmm0, %xmm0
clang creates suboptimal object code for the last instruction (using a 32-bit
offset instead of an 8-bit one):
Disassembly of section .text:
0000000000000000 <.text>:
0: c5 f9 fe 44 07 0c vpaddd 0xc(%rdi,%rax,1),%xmm0,%xmm0
6: c5 f9 fe 44 07 0c vpaddd 0xc(%rdi,%rax,1),%xmm0,%xmm0
c: c5 f9 fe 44 07 0c vpaddd 0xc(%rdi,%rax,1),%xmm0,%xmm0
12: c5 f9 fe 84 07 0c 00 vpaddd 0xc(%rdi,%rax,1),%xmm0,%xmm0
19: 00 00
--
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
