Displaying 5 results from an estimated 5 matches for "movsxd".
Did you mean:
movsd
2011 Mar 19
2
[LLVMdev] Apparent optimizer bug on X86_64
...sult of "1-yylen" which is expected to be
negative, so it should be sign-extended before using its value as rax.
Indexing "in the wrong direction" causes a segfault at the instruction
indicated by '=>'
Here's the disassembly from -O0, which does a sign extension (movsxd):
1300 /*-----------------------------.
1301 | yyreduce -- Do a reduction. |
1302 `-----------------------------*/
1303 yyreduce:
1304 /* yyn is the number of a rule to reduce with. */
1305 yylen = yyr2[yyn];
0x0000000000401069 <+1945>: movsxd rax,DWORD PTR [rbp-0...
2015 Feb 13
2
[LLVMdev] trunk's optimizer generates slower code than 3.5
...shl rax, 20h
mov rsi, offset __mh_execute_header
add rsi, rax
sar rsi, 20h ; size_t
mov edi, 4 ; size_t
call _calloc
lea edx, [r15-1]
movsxd r8, edx
mov ecx, r15d
add ecx, 0FFFFFFFEh
js loc_100000DFA
test r15d, r15d
mov r11d, [rax+r8*4]
jle loc_100000EAE
mov ecx, r15d
add ecx, 0...
2011 Mar 19
0
[LLVMdev] Apparent optimizer bug on X86_64
...ot; which is expected to be
> negative, so it should be sign-extended before using its value as rax.
> Indexing "in the wrong direction" causes a segfault at the instruction
> indicated by '=>'
>
> Here's the disassembly from -O0, which does a sign extension (movsxd):
>
> 1300 /*-----------------------------.
> 1301 | yyreduce -- Do a reduction. |
> 1302 `-----------------------------*/
> 1303 yyreduce:
> 1304 /* yyn is the number of a rule to reduce with. */
> 1305 yylen = yyr2[yyn];
> 0x0000000000401069 <+...
2015 Feb 14
2
[LLVMdev] trunk's optimizer generates slower code than 3.5
...i, offset __mh_execute_header
>> add rsi, rax
>> sar rsi, 20h ; size_t
>> mov edi, 4 ; size_t
>> call _calloc
>> lea edx, [r15-1]
>> movsxd r8, edx
>> mov ecx, r15d
>> add ecx, 0FFFFFFFEh
>> js loc_100000DFA
>> test r15d, r15d
>> mov r11d, [rax+r8*4]
>> jle loc_100000EAE
>>...
2015 Feb 14
2
[LLVMdev] trunk's optimizer generates slower code than 3.5
...add rsi, rax
>>>> sar rsi, 20h ; size_t
>>>> mov edi, 4 ; size_t
>>>> call _calloc
>>>> lea edx, [r15-1]
>>>> movsxd r8, edx
>>>> mov ecx, r15d
>>>> add ecx, 0FFFFFFFEh
>>>> js loc_100000DFA
>>>> test r15d, r15d
>>>> mov r11d, [rax+r8*4]
>>>>...