Re: 4p-1.5-wip with just in time compilation
On Aug 29, 10:50 pm, pablo reda <pablor...@xxxxxxxxx> wrote:
Hi Hellmar
I see you code and the "xchg" asm intruction is slow, change with a
couple of mov !!! and sure gain some speed.
Sure. For first version they where less $HEX things to type and so it
reduced the possibility of a typo that screws a primitive. It's also
sometimes nice to insert a NOP on right place ;)
Regards,
-Helmar
Pablo
.
Relevant Pages
- Re: 4p-1.5-wip with just in time compilation
... I see you code and the "xchg" asm intruction is slow, ... couple of mov!!! ... and sure gain some speed. ...
(comp.lang.forth) - Re: Is Dec function thread safe?
... >>This should only be used to lock the bus prior to XCHG, MOV, IN and ...
(comp.lang.pascal.delphi.misc) - Re: whats the use of "data16 nop" instruction generated by gas on x86 and x86_64
... The basic problem is that there aren't different instruction encodings for 16-bit and 32-bit operations; a code segment has a "default" operand size, and if you want the "other" size, you need the 66h prefix. ... For instance, in 16-bit mode a "MOV AX, BX" can be turned into "MOV EAX, EBX" by adding a 66h prefix. ... 90h is the opcode for XCHG AX,AX, so adding one or more 66h prefix bytes change the code from 16 to 32 bit or vice versa. ... BTW, MOVing any register to itself is a two-byte NO-OP, but unlike the 66h/90h combination it isn't specialcased by the decoder, so it does affect the reorder buffer register pressure. ...
(comp.arch) - Re: [RosAsm example]
... 'XCHG reg,mem ' got same latency as Push/Pop ... 'XCHG reg,mem (esp or ebp)' is a bit faster. ... So XCHG mem is always faster than two lines with mov from and to memory. ... eax isn't defined yet? ...
(alt.lang.asm) - Re: [RosAsm example]
... 'XCHG reg,mem ' got same latency as Push/Pop ... 'XCHG reg,mem (esp or ebp)' is a bit faster. ... So XCHG mem is always faster than two lines with mov from and to memory. ... eax isn't defined yet? ...
(alt.lang.asm) |
|
