[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Abysmal performance with new gccs
- To: R Clint Whaley <[email protected]>
- Subject: Re: Abysmal performance with new gccs
- From: Julian Ruhe <[email protected]>
- Date: Wed, 01 Aug 2001 23:43:16 +0200
- CC: [email protected]
- Organization: TU Berlin
- References: <[email protected]>
- User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:0.9.1) Gecko/20010607 Netscape6/6.1b1
Hello Clint,
>fxch between a lot of the faddp and fmul instructions. If I remember correctly
>fxch is an inst. to swap registers on the x87 stack (anyone want to correct
>me on this?), which is free if done in the right place.
>
FXCH is not "free"! It is only free in a way that it uses no functional
unit resources, but it is a real x86
instruction which consumes the same decoding bandwidth as every other
direct path instruction (Athlon
can decode three direct path instructions per cycle).
Regards
Julian
p.s. Clint, I am back from vacation - more tomorrow (Athlon kernel!)...