Forum > GPU crunching

C-60 APU and Radeon HD6920

<< < (3/7) > >>

Raistmer:
Fine (if it can be fine at all) you just confirmed my own observations!
Same distribution here (I tried SSE-nly build too also, it works).

EDIT: no, not exactly the same. I have SSE2 not working too and it works on your CPU...
But all x64 fail here too...

Mike:

--- Quote from: Raistmer on 03 Jan 2012, 02:58:56 pm ---Fine (if it can be fine at all) you just confirmed my own observations!
Same distribution here (I tried SSE-nly build too also, it works).

EDIT: no, not exactly the same. I have SSE2 not working too and it works on your CPU...
But all x64 fail here too...

--- End quote ---

No SSE2 dont work here also.


--- Quote ---Only 3 versions are functioning.
SSE3_AMD, SSE3_INTEL and SSE4.1
--- End quote ---

Mike:

Here is my full bench SSE3_AMD vs SSE3_Intel.
Intel version is faster on each angle range. 

AK_v8b2_win_SSE3_AMD.exe -verb -nog / PG0009.wu :
AppName: AK_v8b2_win_SSE3_AMD.exe
AppArgs: -verb -nog
TaskName: PG0009.wu
Started at  : 20:28:36.375
Ended at    : 20:35:54.376
    437.939 secs Elapsed
    431.670 secs CPU time

AK_v8b2_win_SSE3_INTEL.exe -verb -nog / PG0009.wu :
AppName: AK_v8b2_win_SSE3_INTEL.exe
AppArgs: -verb -nog
TaskName: PG0009.wu
Started at  : 20:35:58.245
Ended at    : 20:43:11.676
    433.368 secs Elapsed
    426.881 secs CPU time

AK_v8b2_win_SSE3_AMD.exe -verb -nog / PG0395.wu :
AppName: AK_v8b2_win_SSE3_AMD.exe
AppArgs: -verb -nog
TaskName: PG0395.wu
Started at  : 20:43:15.513
Ended at    : 20:50:10.863
    415.288 secs Elapsed
    409.643 secs CPU time

------------
AK_v8b2_win_SSE3_INTEL.exe -verb -nog / PG0395.wu :
AppName: AK_v8b2_win_SSE3_INTEL.exe
AppArgs: -verb -nog
TaskName: PG0395.wu
Started at  : 20:50:14.732
Ended at    : 20:56:58.086
    403.291 secs Elapsed
    397.771 secs CPU time

AK_v8b2_win_SSE3_AMD.exe -verb -nog / PG0444.wu :
AppName: AK_v8b2_win_SSE3_AMD.exe
AppArgs: -verb -nog
TaskName: PG0444.wu
Started at  : 20:57:01.892
Ended at    : 21:02:46.090
    344.136 secs Elapsed
    339.521 secs CPU time

AK_v8b2_win_SSE3_INTEL.exe -verb -nog / PG0444.wu :
AppName: AK_v8b2_win_SSE3_INTEL.exe
AppArgs: -verb -nog
TaskName: PG0444.wu
Started at  : 21:02:49.866
Ended at    : 21:08:18.339
    328.411 secs Elapsed
    324.139 secs CPU time

AK_v8b2_win_SSE3_AMD.exe -verb -nog / PG1327.wu :
AppName: AK_v8b2_win_SSE3_AMD.exe
AppArgs: -verb -nog
TaskName: PG1327.wu
Started at  : 21:08:22.177
Ended at    : 21:13:09.638
    287.399 secs Elapsed
    283.189 secs CPU time

AK_v8b2_win_SSE3_INTEL.exe -verb -nog / PG1327.wu :
AppName: AK_v8b2_win_SSE3_INTEL.exe
AppArgs: -verb -nog
TaskName: PG1327.wu
Started at  : 21:13:13.491
Ended at    : 21:17:48.753
    275.200 secs Elapsed
    270.443 secs CPU time

Jason G:

--- Quote from: Mike on 03 Jan 2012, 06:17:35 pm ---Intel version is faster on each angle range. 
--- End quote ---

That's great news!, probably means the caching & SSE3 implementation is improved enough in that model to negate the need for a special AMD build with the earlier libraries.  That probably means 1 less build already, if we can manage to statically link in the libs needed by the older AMD chips  :)  I think the Instruction set convergence will end up making things substantially easier, so we can get back to optimisation instead of build & library juggling.  Here's hoping  ;)

Raistmer:
I would not talk about any convergence after these tests done. Looks like divergence much more adequate term...
Look for number of builds that DON'T run on these new AMD chips...
Whole x64 AKv8b2 set fails to even report error...

Navigation

[0] Message Index

[#] Next page

[*] Previous page

Go to full version