DiabloMiner GPU Miner

[djinfected]

New problem.

Code:

PS C:\Program Files (x86)\Bitcoin> .\bpm

C:\Program Files (x86)\Bitcoin>cd "C:\Program Files (x86)\Bitcoin\DiabloMiner"

C:\Program Files (x86)\Bitcoin\DiabloMiner>DiabloMiner-Windows.exe --url http://username:password@api2.bitcoin.cz:8332/ -w 64 -f 1000
Picked up _JAVA_OPTIONS: -Xmx1024M -Xms1024M
[1/31/12 12:23:53 PM] Started
[1/31/12 12:23:53 PM] Connecting to: http://api2.bitcoin.cz:8332/
[1/31/12 12:23:53 PM] Using NVIDIA CUDA OpenCL 1.1 CUDA 4.1.1
[1/31/12 12:23:53 PM] Added GeForce 9600 GT (#1) (8 CU, local work size of 64)
[1/31/12 12:24:25 PM] api2.bitcoin.cz accepted block 1 from GeForce 9600 GT (#1)
[1/31/12 12:32:51 PM] api2.bitcoin.cz accepted block 2 from GeForce 9600 GT (#1)
[1/31/12 12:33:54 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 12:37:52 PM] api2.bitcoin.cz accepted block 3 from GeForce 9600 GT (#1)
[1/31/12 12:43:54 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 12:45:00 PM] api2.bitcoin.cz accepted block 4 from GeForce 9600 GT (#1)
[1/31/12 12:53:55 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 1:04:19 PM] api2.bitcoin.cz accepted block 5 from GeForce 9600 GT (#1)
[1/31/12 1:06:31 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 1:09:21 PM] api2.bitcoin.cz accepted block 6 from GeForce 9600 GT (#1)
[1/31/12 1:09:42 PM] api2.bitcoin.cz accepted block 7 from GeForce 9600 GT (#1)
[1/31/12 1:10:02 PM] api2.bitcoin.cz accepted block 8 from GeForce 9600 GT (#1)
[1/31/12 1:16:32 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 1:18:37 PM] api2.bitcoin.cz accepted block 9 from GeForce 9600 GT (#1)
[1/31/12 1:21:46 PM] api2.bitcoin.cz accepted block 10 from GeForce 9600 GT (#1)
[1/31/12 1:28:15 PM] api2.bitcoin.cz accepted block 11 from GeForce 9600 GT (#1)
[1/31/12 1:30:18 PM] api2.bitcoin.cz accepted block 12 from GeForce 9600 GT (#1)
[1/31/12 1:37:34 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 1:39:16 PM] api2.bitcoin.cz accepted block 13 from GeForce 9600 GT (#1)
[1/31/12 1:50:39 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 2:00:19 PM] api2.bitcoin.cz accepted block 14 from GeForce 9600 GT (#1)
[1/31/12 2:00:40 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 2:02:50 PM] api2.bitcoin.cz accepted block 15 from GeForce 9600 GT (#1)
[1/31/12 2:05:33 PM] api2.bitcoin.cz accepted block 16 from GeForce 9600 GT (#1)
[1/31/12 2:14:22 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 2:14:48 PM] api2.bitcoin.cz accepted block 17 from GeForce 9600 GT (#1)
[1/31/12 2:15:47 PM] api2.bitcoin.cz accepted block 18 from GeForce 9600 GT (#1)
[1/31/12 2:33:00 PM] api2.bitcoin.cz accepted block 19 from GeForce 9600 GT (#1)
[1/31/12 2:33:47 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 2:35:39 PM] api2.bitcoin.cz accepted block 20 from GeForce 9600 GT (#1)
[1/31/12 2:37:21 PM] api2.bitcoin.cz accepted block 21 from GeForce 9600 GT (#1)
[1/31/12 2:46:20 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 2:51:20 PM] api2.bitcoin.cz accepted block 22 from GeForce 9600 GT (#1)
[1/31/12 2:53:08 PM] api2.bitcoin.cz accepted block 23 from GeForce 9600 GT (#1)
[1/31/12 3:03:03 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 3:13:04 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 3:20:23 PM] api2.bitcoin.cz accepted block 24 from GeForce 9600 GT (#1)
[1/31/12 3:20:55 PM] api2.bitcoin.cz accepted block 25 from GeForce 9600 GT (#1)
[1/31/12 3:23:05 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 3:27:29 PM] api2.bitcoin.cz accepted block 26 from GeForce 9600 GT (#1)
[1/31/12 3:39:03 PM] api2.bitcoin.cz accepted block 27 from GeForce 9600 GT (#1)
[1/31/12 3:59:10 PM] api2.bitcoin.cz accepted block 28 from GeForce 9600 GT (#1)
[1/31/12 4:03:22 PM] api2.bitcoin.cz accepted block 29 from GeForce 9600 GT (#1)
[1/31/12 4:06:18 PM] api2.bitcoin.cz accepted block 30 from GeForce 9600 GT (#1)
[1/31/12 4:10:14 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 4:17:56 PM] api2.bitcoin.cz accepted block 31 from GeForce 9600 GT (#1)
[1/31/12 4:25:30 PM] api2.bitcoin.cz accepted block 32 from GeForce 9600 GT (#1)
[1/31/12 4:29:24 PM] ERROR: Cannot connect to api2.bitcoin.cz: Read timed out
[1/31/12 4:35:10 PM] api2.bitcoin.cz accepted block 33 from GeForce 9600 GT (#1)
[1/31/12 4:37:15 PM] api2.bitcoin.cz accepted block 34 from GeForce 9600 GT (#1)
[1/31/12 4:38:16 PM] api2.bitcoin.cz accepted block 35 from GeForce 9600 GT (#1)
[1/31/12 4:49:26 PM] api2.bitcoin.cz rejected block 1 from GeForce 9600 GT (#1)
[1/31/12 4:52:59 PM] ERROR: Failed to queue kernel, error -5

Every time I run your miner, eventually it crashes. This time I ran it in Powershell to make sure the error would stay up and this is what I got (but I can't prove that the other times were from the same cause).

[1714139479]

1714139479

[DiabloD3]

Code:

[1/31/12 4:52:59 PM] ERROR: Failed to queue kernel, error -5

-5 == CL_OUT_OF_RESOURCES == driver bug.

[djinfected]

Code:

[1/31/12 4:52:59 PM] ERROR: Failed to queue kernel, error -5

-5 == CL_OUT_OF_RESOURCES == driver bug.

Gracias, amigo. ;-;

[Roadhog2k5]

7970 tweaks?

[DiabloD3]

7970 tweaks?

I've been on a 3 "day" almost interrupted hackfest trying to make SDK 2.6 suck less dick.

My brain is starting to melt after 24-hours-straight sessions.

Good news is: I seem to be winning, and I think I'm almost done.

Bad news is: the kernel is almost unrecognizable, and its known to the state of California to cause cancer in rats.

More bad news: I have no clue what its going to do to GCN.

[Keninishna]

7970 tweaks?

I've been on a 3 "day" almost interrupted hackfest trying to make SDK 2.6 suck less dick.

My brain is starting to melt after 24-hours-straight sessions.

Good news is: I seem to be winning, and I think I'm almost done.

Bad news is: the kernel is almost unrecognizable, and its known to the state of California to cause cancer in rats.

More bad news: I have no clue what its going to do to GCN.

I'll remember not to eat the kernel but keep winning and GCN likes the abuse.

[rjk]

7970 tweaks?

I've been on a 3 "day" almost interrupted hackfest trying to make SDK 2.6 suck less dick.

My brain is starting to melt after 24-hours-straight sessions.

Good news is: I seem to be winning, and I think I'm almost done.

Bad news is: the kernel is almost unrecognizable, and its known to the state of California to cause cancer in rats.

More bad news: I have no clue what its going to do to GCN.

I can't wait.

See? Give a dev some specs, and he'll code for a day, but buy him a fucking awesome card and he will pour out his heart and soul into making a better miner. Kudos.

[Frizz23]

Which flags do I have to use to get the best out of my 7970?

[DiabloD3]

Which flags do I have to use to get the best out of my 7970?

ATM -v 1, but who knows once I finish this more optimized kernel.

[film2240]

Is there a windows GUI version of Diablo miner? Like GUIMiner but without the constant connection dropouts.Can diablo be launched from GUIMiner?

[Roadhog2k5]

Which flags do I have to use to get the best out of my 7970?

ATM -v 1, but who knows once I finish this more optimized kernel.

Any faster so far?

[DiabloD3]

Which flags do I have to use to get the best out of my 7970?

ATM -v 1, but who knows once I finish this more optimized kernel.

Any faster so far?

This is a two stage project. I'm almost done stage 1.

Old kernel:
-v 1 sdk 2.6 = 883 ops 13 registers, 2.1 = 803 ops 17 registers
-v 2 sdk 2.6 = 1503 ops 21 registers, 2.1 = 1362 ops 21 registers

2.6 is 10% slower than 2.1.

New kernel:
-v 1 sdk 2.6 = 827 ops 21 registers, 828 ops 20 registers
-v 2 sdk 2.6 = 1464 36 registers, 2.1 = 1402 ops 37 registers

2.6 is 4% slower than 2.1.

New vs old:
-v 1 =~ 7% faster 2.6, 3% slower 2.1, 2.6 is 21% away from minimum target of 681 ops
-v 2 =~ 3% slower 2.6, 3% slower 2.1, 2.6 is 8% away from minimum target of 1362 ops

After looking at the ops generated in the .isa output, I'm clearly starting to force 2.6 to act more like the 2.1 results, so I seem to be getting somewhere. The hard part is going to be ordering instructions to properly saturate ALU clauses on vliw5 and GCN both.

[Roadhog2k5]

After looking at the ops generated in the .isa output, I'm clearly starting to force 2.6 to act more like the 2.1 results, so I seem to be getting somewhere. The hard part is going to be ordering instructions to properly saturate ALU clauses on vliw5 and GCN both.

Wouldn't it be easier and more efficient just to have a separate kernel for GCN? It's a totally different architecture so it would make sense to, right?

[DiabloD3]

After looking at the ops generated in the .isa output, I'm clearly starting to force 2.6 to act more like the 2.1 results, so I seem to be getting somewhere. The hard part is going to be ordering instructions to properly saturate ALU clauses on vliw5 and GCN both.

Wouldn't it be easier and more efficient just to have a separate kernel for GCN? It's a totally different architecture so it would make sense to, right?

Nope, that makes no sense. Its still the same compiler, and OpenCL is a generic language meant for wildly different hardware. This kernel runs on everything from x86 to ARM to Sparc to POWER and PPC to Cell SPUs to Intel GPUs (if/when Intel actually fixes their drivers) to Nvidia to even certain DSPs.

A compiler is free to completely ignore the specific ordering of instructions I am using in the kernel and optimize it correctly for it's target hardware. AMD's doesn't, and takes significant hinting from the code to allow developers to influence the output. This is arguably both right and wrong, given how much code effects/is effected by bandwidth usage and latency and other things.

The difference between 2.6 and 2.1 is that 2.6 is tuned differently, and 2.6 allows much more hinting from the kernel layout. The compiler could freely reorder everything safely to give full performance, its just difficult on complex hardware like this; 2.1 went farther into this than 2.6 does.

I'm slightly surprised I actually need to do this, however, because AMD uses LLVM in their compiler, which is very good at SSA tree optimizations. Arguably, its rather good at what I'm doing by hand.

[DiabloD3]

Done stage 1:

Old kernel:
-v 1 sdk 2.6 = 883 ops 13 registers, 2.1 = 803 ops 17 registers
-v 2 sdk 2.6 = 1503 ops 21 registers, 2.1 = 1362 ops 21 registers

2.6 is 10% slower than 2.1.

New kernel:
-v 1 sdk 2.6 = 886 ops 23 registers, 887 ops 21 registers
-v 2 sdk 2.6 = 1395 39 registers, 2.1 = 1396 ops 36 registers

2.6 is tied with 2.1.

New vs old:
-v 1 =~ 0% faster 2.6, 10% slower 2.1, 2.6 is 30% away from minimum target of 681 ops
-v 2 =~ 8% faster 2.6, 2% slower 2.1, 2.6 is 2% away from minimum target of 1362 ops

If I committed this right now, 2.1 users could switch to 2.6 and not see a real difference in speed.

Now I begin stage 2: optimum ALU clause packing and register use reduction.

Edit: Somehow I got the new numbers wrong, lets try that again.

[Avid6eek]

Awesome job Diablo...I can't wait to see what the end results are.

I just moved over to your miner after GUIMiner went down and cgminer simply wasn't performing.  I'm happy with the performance on my current setup, but am closely following your progress as I have plans for GCN miners in the near future.

[Joshwaa]

Diablo I have 3 7970's let me know if you need testing done.  Right now I am using Diablo no flags getting 680MHash/s 1144core/685mem.

[jjiimm_64]

anyone having problems using diablo with gpumax.com ?   

syptoms:
  start.  works OK.  hashrate good.
  during:  start to get connection issues reported by diablo, but it reconnects and works.
  after a while:  the connection issues increase to the point that no shares are accepted.  but it reports a full hashrate.

fix:  stop and start diablo

[DiabloD3]

anyone having problems using diablo with gpumax.com ?  

syptoms:
  start.  works OK.  hashrate good.
  during:  start to get connection issues reported by diablo, but it reconnects and works.
  after a while:  the connection issues increase to the point that no shares are accepted.  but it reports a full hashrate.

fix:  stop and start diablo

I thought gpumax was a scam?

Edit: Apparently its not, others on the forum are just morons

[DiabloD3]

Diablo I have 3 7970's let me know if you need testing done.  Right now I am using Diablo no flags getting 680MHash/s 1144core/685mem.

Don't need external testing. The community donated enough that I can go buy a 7970 of my own now (thanks everyone!), but my 5850 testing just isn't done yet. I think after this current round of optimization hunting I'll finally switch.