[Bug target/34653] unnecessary REX prefix

[pinskia at gcc dot gnu dot org]

-- 

pinskia at gcc dot gnu dot org changed:

   What|Removed |Added

   Severity|normal  |enhancement


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34653

[Bug target/34653] unnecessary REX prefix

[dean at arctic dot org]

--- Comment #1 from dean at arctic dot org  2008-01-03 19:27 ---
oops i should have used an "unsigned long" for the tag rather than unsigned
long long, not that it matters much.

here's an expanded example showing another unnecessary REX:

extern unsigned long table[];

unsigned long foo(unsigned char *p) {
  unsigned long tag = *p;
  return table[tag >> 4] + table[tag & 0xf];
}

which generates:

   0:   0f b6 17movzbl (%rdi),%edx
   3:   48 89 d0mov%rdx,%rax
   6:   48 c1 ea 04 shr$0x4,%rdx
   a:   83 e0 0fand$0xf,%eax
   d:   48 8b 04 c5 00 00 00mov0x0(,%rax,8),%rax
  14:   00
11: R_X86_64_32Stable
  15:   48 03 04 d5 00 00 00add0x0(,%rdx,8),%rax
  1c:   00
19: R_X86_64_32Stable
  1d:   c3  retq

and in this case the "mov %rdx,%rax" could be "mov %edx,%eax" because of the
dominating movzbl.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34653

[Bug target/34653] unnecessary REX prefix

[ubizjak at gmail dot com]

--- Comment #2 from ubizjak at gmail dot com  2009-09-17 09:50 ---
(In reply to comment #1)

> and in this case the "mov %rdx,%rax" could be "mov %edx,%eax" because of the
> dominating movzbl.

32bit moves and other instructions _SIGN_EXTEND_ results to 64bits on x86_64.


-- 

ubizjak at gmail dot com changed:

   What|Removed |Added

 Status|UNCONFIRMED |RESOLVED
 Resolution||INVALID


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34653

[Bug target/34653] unnecessary REX prefix

[dean at arctic dot org]

--- Comment #3 from dean at arctic dot org  2009-09-17 10:23 ---
(In reply to comment #2)
> (In reply to comment #1)
> 
> > and in this case the "mov %rdx,%rax" could be "mov %edx,%eax" because of the
> > dominating movzbl.
> 
> 32bit moves and other instructions _SIGN_EXTEND_ results to 64bits on x86_64.
> 

every single data type in my example was unsigned.


-- 

dean at arctic dot org changed:

   What|Removed |Added

 Status|RESOLVED|UNCONFIRMED
 Resolution|INVALID |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34653

[Bug target/34653] unnecessary REX prefix

[dean at arctic dot org]

--- Comment #4 from dean at arctic dot org  2009-09-17 10:27 ---
(In reply to comment #2)
> 32bit moves and other instructions _SIGN_EXTEND_ results to 64bits on x86_64

wait i just reread your statement.

the amd64 ISA zero-extends 32-bit register writes out to 64-bits.  please go
read the documentation.

-dean


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34653

[Bug target/34653] unnecessary REX prefix

[hjl dot tools at gmail dot com]

--- Comment #5 from hjl dot tools at gmail dot com  2009-09-17 13:47 ---
This is a dup for PR 17387.

*** This bug has been marked as a duplicate of 17387 ***


-- 

hjl dot tools at gmail dot com changed:

   What|Removed |Added

 Status|UNCONFIRMED |RESOLVED
 Resolution||DUPLICATE


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34653