jedi95
|
|
May 17, 2011, 12:41:16 AM |
|
5xxx maxes out at a worksize of 256.
My dual 5870 (w/o CF bridges) maxes out at WORKSIZE=128. Nope, that too maxes out at 256. What I said was 768 simply is not valid for 5xxx hardware. Phoenix should output the error OpenCL is returning instead of covering it up. I'll probably add this in the next version, but for now it just uses the maximum supported if you enter a higher value.
|
Phoenix Miner developer Donations appreciated at: 1PHoenix9j9J3M6v3VQYWeXrHPPjf7y3rU
|
|
|
rowbot
Member
Offline
Activity: 96
Merit: 10
NOW
|
|
May 17, 2011, 12:40:07 PM |
|
Tried it on my 5830 and there was no difference.
|
|
|
|
Folax
|
|
May 21, 2011, 10:48:53 AM |
|
Works nicely on XP64. Anyone using it on Linux?
|
My GF thinks I'm useless, if you think otherwise and can proof it to her, please do so and donate: 14wG6u2bAD9q1nLmLL9MST1ZzbTE9Pt8nG
|
|
|
William Reed
Newbie
Offline
Activity: 15
Merit: 0
|
|
May 21, 2011, 03:05:57 PM |
|
Works very well. I am getting over 440 Mhash/s on HD 5870 (1000/375) with -k phatk AGGRESSION=13 WORKSIZE=256 VECTORS BFI_INT and about 416 Mhash/s on poclbm. However my other HD 5870 running at 950/375 with same switches only hashes about 410 MHash/s with phatk while poclbm gives about 400MHash/s.
|
|
|
|
JayC
Newbie
Offline
Activity: 34
Merit: 0
|
|
May 21, 2011, 03:23:52 PM |
|
Works very well. I am getting over 440 Mhash/s on HD 5870 (1000/375) with -k phatk AGGRESSION=13 WORKSIZE=256 VECTORS BFI_INT and about 416 Mhash/s on poclbm. However my other HD 5870 running at 950/375 with same switches only hashes about 410 MHash/s with phatk while poclbm gives about 400MHash/s.
Just out of curiosity, how do you tell what worksize you need for a specific card?
|
|
|
|
huayra.agera
|
|
May 21, 2011, 05:47:35 PM |
|
Works very well. I am getting over 440 Mhash/s on HD 5870 (1000/375) with -k phatk AGGRESSION=13 WORKSIZE=256 VECTORS BFI_INT and about 416 Mhash/s on poclbm. However my other HD 5870 running at 950/375 with same switches only hashes about 410 MHash/s with phatk while poclbm gives about 400MHash/s.
This worked well for me! Thanks for this tip man! +1: I have 3 5850s and these settings added like 20 Mhash/s while on my 6850 +10Mh/s! Cool!
|
BTC: 1JMPScxohom4MXy9X1Vgj8AGwcHjT8XTuy
|
|
|
lagmo
Member
Offline
Activity: 67
Merit: 10
|
|
May 21, 2011, 06:17:20 PM |
|
Very nice job! Finally got to break the 400Mhash/s barrier on my HD5850, an increase of about 8-10Mhash/s over POCLBM kernel.
|
|
|
|
William Reed
Newbie
Offline
Activity: 15
Merit: 0
|
|
May 21, 2011, 07:10:55 PM |
|
Works very well. I am getting over 440 Mhash/s on HD 5870 (1000/375) with -k phatk AGGRESSION=13 WORKSIZE=256 VECTORS BFI_INT and about 416 Mhash/s on poclbm. However my other HD 5870 running at 950/375 with same switches only hashes about 410 MHash/s with phatk while poclbm gives about 400MHash/s.
Just out of curiosity, how do you tell what worksize you need for a specific card? There is no general rule. It mostly depends on the architecture and memory technology used. In heavy scientific calculations best worksize is usually the one that the card can process natively but in mining where a single loop is very simple and fast the optimal worksize can vary. In mining lowering memory clocks saves power and therefore may allow for extra OC on the core thus speeding up computation. If you lower your memory clocks too much it can lower your processing power but this kind of loss can be compensated by lowering worksize. So without solid background in high speed computation architectures the fastest way to know is trying out all possible combinations.
|
|
|
|
Syke
Legendary
Offline
Activity: 3878
Merit: 1193
|
|
May 24, 2011, 05:23:40 PM |
|
Any chance of getting a kernel optimized for the 6xxx series?
|
Buy & Hold
|
|
|
EPiSKiNG
Legendary
Offline
Activity: 800
Merit: 1001
|
|
May 25, 2011, 09:19:28 PM |
|
Any chance of getting a kernel optimized for the 6xxx series?
+1 !!
|
|
|
|
tiberiandusk
|
|
May 26, 2011, 04:39:25 AM |
|
My experience with my 5870 shows that worksize=128 works the best. With worksize=256 I show a slightly higher hashrate but overall submitted shares goes down a bit.
|
|
|
|
AngelusWebDesign
|
|
June 03, 2011, 05:07:55 PM |
|
Hashkill is faster for me on Linux 64-bit.
|
|
|
|
allinvain
Legendary
Offline
Activity: 3080
Merit: 1080
|
|
June 04, 2011, 09:00:46 AM |
|
Hashkill is faster for me on Linux 64-bit.
Hmm, wish they'd release a windblowz binary soon
|
|
|
|
dishwara
Legendary
Offline
Activity: 1855
Merit: 1016
|
|
June 04, 2011, 05:28:05 PM |
|
Waiting for windows version, so i too can get more hashes.
|
|
|
|
redcodenl
Newbie
Offline
Activity: 12
Merit: 0
|
|
June 07, 2011, 07:10:01 PM |
|
Any chance of getting a kernel optimized for the 6xxx series?
+1 as well! I'm now using phatk (with Phoenix) for my double 6870's, it is working like a charm. But the tought that it might do better with an optimized kernel is killing me ;-) Are there indications a better/optimized kernel for the 6xxx series can be created?
|
|
|
|
mbraun
Newbie
Offline
Activity: 2
Merit: 0
|
|
June 11, 2011, 02:52:33 PM |
|
HD5830 (Sapphire, stock volts) with SDK 2.4 VECTORS BFI_INT AGGRESSION=12 DEVICE=0 FASTLOOP=false WORKSIZE=256
1000/300: 298MH/s, 66°C 1000/300: 310MH/s, 66°C (phatk)
Thanks a lot man!
|
|
|
|
hugolp
Legendary
Offline
Activity: 1148
Merit: 1001
Radix-The Decentralized Finance Protocol
|
|
June 11, 2011, 03:13:45 PM |
|
My experience with my 5870 shows that worksize=128 works the best. With worksize=256 I show a slightly higher hashrate but overall submitted shares goes down a bit.
How is this posible?
|
|
|
|
hchc
|
|
June 11, 2011, 04:11:07 PM |
|
Hashkill is faster for me on Linux 64-bit.
can you post some number? I'm contemplating switching from windows to linux just because of this and not sure if its worth while. Currentlly getting 300mh/s with 5830 at 970/300..
|
|
|
|
............
| . | ▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▀ ▀▓▓▓▀ ▀▓▓▀ ▀▓▓▓▓ ▓▓▓▓▓▄ ▄▓▓▓▄ ▄▓▓▄ ▄▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓▓▓▀ ▀▓▓▓▓▓ ▓▓▓▓▓▓▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓▓▓▄ ▄▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▀ ▀▓▓▓▀ ▀▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▄ ▄▓▓▓▄ ▄▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
| . | | . | ▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▀ ▀▓▓▓▀ ▀▓▓▀ ▀▓▓▓▓ ▓▓▓▓▓▄ ▄▓▓▓▄ ▄▓▓▄ ▄▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓▓▓▀ ▀▓▓▓▓▓ ▓▓▓▓▓▓▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓▓▓▄ ▄▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▀ ▀▓▓▓▀ ▀▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▄ ▄▓▓▓▄ ▄▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▀ ▀▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▄ ▄▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
| . | ............
|
|
|
|
mbraun
Newbie
Offline
Activity: 2
Merit: 0
|
|
June 11, 2011, 06:41:34 PM |
|
can you post some number? I'm contemplating switching from windows to linux just because of this and not sure if its worth while. Currentlly getting 300mh/s with 5830 at 970/300..
These are already great numbers, don't think they'll change much on linux or windows. I also do not believe that mining gets faster because the CPU is able to work 64bits in a single cycle. It's not GPU related.
|
|
|
|
Hawkix
|
|
June 27, 2011, 09:08:35 PM |
|
Phateus, would you consider to replace the Ma() macro as suggested by bitless and re-run the ATI optimization to check if it can be further improved? Bitless saved 1 operation from each Ma() call. Maybe, with some re-ordering, this can be optimized further.
|
|
|
|
|