INTEL Arc.

Ian&Steve C.
Ian&Steve C.
Joined: 19 Jan 20
Posts: 3681
Credit: 33818304266
RAC: 37819403

I see you picked up 2x gamma

I see you picked up 2x gamma ray tasks for the ARC, will check back later to see how they ran.

_________________________________________________________________________

[AF>EDLS]zOU
[AF>EDLS]zOU
Joined: 5 May 15
Posts: 65
Credit: 384235373
RAC: 1616

Ian&Steve C. wrote: I see

Ian&Steve C. wrote:

I see you picked up 2x gamma ray tasks for the ARC, will check back later to see how they ran.

 

I pauded the pending 1.70 Binary Radio Pulsar Search (Arecibo) (opencl-intel_gpu-newer) to run the 1.22 Gamma-ray pulsar binary search #1 on GPUs (FGRPopencl-intel_gpu) earlier

[AF>EDLS]zOU
[AF>EDLS]zOU
Joined: 5 May 15
Posts: 65
Credit: 384235373
RAC: 1616

Ian&Steve C. wrote:I see

Ian&Steve C. wrote:

I see you picked up 2x gamma ray tasks for the ARC, will check back later to see how they ran.

 

I paused the pending 1.70 Binary Radio Pulsar Search (Arecibo) (opencl-intel_gpu-newer) to run the 1.22 Gamma-ray pulsar binary search #1 on GPUs (FGRPopencl-intel_gpu) earlier

 

Edit:
Einstein@Home    1.22 Gamma-ray pulsar binary search #1 on GPUs (FGRPopencl-intel_gpu)    LATeah3012L12221022_836.0_0_0.0_2286342_1    00:29:50 (00:29:41)    99,49    70.03 MB    89,998    00:10:43    13d,22:31:18    1C + 1INT    Running    48,0 °C    0    A750    
 

This one has been "stuck" at 89.998% for about 15mn.... but has completed
https://einsteinathome.org/task/1375878092

OpenCL compiling FAILED! : -11 . Error message: 1:10:30: error: unknown type name 'double2'; did you mean 'double'? __kernel void test( __global double2 *vec) { ^~~~~~~ double 1:10:30: error: use of type 'double' requires cl_khr_fp64 extension to be enabled OpenCL device has no FP64 support</p>

<p>

[AF>EDLS]zOU
[AF>EDLS]zOU
Joined: 5 May 15
Posts: 65
Credit: 384235373
RAC: 1616

Well, it has been validated

Well, it has been validated without FP64.
https://einsteinathome.org/task/1375878092

https://einsteinathome.org/task/1375878090

Granted credit:3,465

[AF>EDLS]zOU
[AF>EDLS]zOU
Joined: 5 May 15
Posts: 65
Credit: 384235373
RAC: 1616

TASK ID WORKUNIT

TASK ID WORKUNIT ID SENT TIME REPORTED OR DEADLINE STATUS RUN TIME CPU TIME GRANTED CREDIT

Application

p2030.20200424.G52.55-03.62.C.b6s0g0.00000_2032_1 683330066 4 Nov 2022 12:37:39 UTC 4 Nov 2022 13:18:51 UTC Completed and validated 2 0 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b6s0g0.00000_225_1 683328259 4 Nov 2022 13:18:51 UTC 4 Nov 2022 14:50:24 UTC Completed and validated 49 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b6s0g0.00000_228_1 683328262 4 Nov 2022 13:18:51 UTC 4 Nov 2022 14:43:01 UTC Completed and validated 50 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b6s0g0.00000_241_1 683328275 4 Nov 2022 13:18:51 UTC 4 Nov 2022 14:46:39 UTC Completed and validated 50 42 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b5s0g0.00000_3164_1 683405493 4 Nov 2022 12:59:50 UTC 4 Nov 2022 14:38:51 UTC Completed and validated 46 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b5s0g0.00000_3165_1 683405494 4 Nov 2022 12:59:50 UTC 4 Nov 2022 14:38:51 UTC Completed and validated 47 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b6s0g0.00000_1227_2 683329261 4 Nov 2022 14:40:57 UTC 4 Nov 2022 16:10:45 UTC Completed and validated 49 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b5s0g0.00000_567_1 683402896 4 Nov 2022 13:18:51 UTC 4 Nov 2022 14:50:24 UTC Completed and validated 49 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.68-03.84.C.b0s0g0.00000_832_2 683253523 4 Nov 2022 12:35:35 UTC 4 Nov 2022 12:37:39 UTC Completed and validated 41 40 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200424.G52.55-03.62.C.b5s0g0.00000_2458_1 683404787 4 Nov 2022 13:43:07 UTC 4 Nov 2022 14:56:40 UTC Completed and validated 53 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
p2030.20200327.G51.11-03.83.S.b1s0g0.00000_1628_2 680284758 4 Nov 2022 12:59:50 UTC 4 Nov 2022 14:38:51 UTC Completed and validated 51 41 62 Binary Radio Pulsar Search (Arecibo) v1.70 () windows_x86_64
LATeah3012L12221022_836.0_0_0.0_2285703_1 683583189 4 Nov 2022 14:07:35 UTC 4 Nov 2022 16:07:06 UTC Completed and validated 1,785 1,773 3,465 Gamma-ray pulsar binary search #1 on GPUs v1.22 () windows_x86_64
LATeah3012L12221022_836.0_0_0.0_2286342_1 683583190 4 Nov 2022 14:07:35 UTC 4 Nov 2022 15:37:26 UTC Completed and validated 1,802 1,791 3,465 Gamma-ray pulsar binary search #1 on GPUs v1.22 () windows_x86_64

Ian&Steve C.
Ian&Steve C.
Joined: 19 Jan 20
Posts: 3681
Credit: 33818304266
RAC: 37819403

I wonder if that last FP64

I wonder if that last FP64 section (the final 10%) fell back to the CPU for processing and that's why it took so long. or it uses some other technique to kinda sorta do FP64 work really slowly using multiple clock cycles on the FP32 cores.

do you recall how long it took to get from 0% to 89%?

 

but this seems to confirm what some earlier reports said, no hardware FP64 support on these cards.

_________________________________________________________________________

[AF>EDLS]zOU
[AF>EDLS]zOU
Joined: 5 May 15
Posts: 65
Credit: 384235373
RAC: 1616

Ian&Steve C. wrote:do you

Ian&Steve C. wrote:

do you recall how long it took to get from 0% to 89%?

seems to be about 7mn (I just managed to capture it on a currently running one)

Einstein@Home    1.22 Gamma-ray pulsar binary search #1 on GPUs (FGRPopencl-intel_gpu)    LATeah3012L12221022_820.0_0_0.0_1667151_2    00:07:05 (00:06:58)    98,34    133.97 MB    89,998    00:07:07    13d,22:19:33    1C + 1INT    Running    53,2 °C    0    A750    
 

 

edit:

28mn total
Einstein@Home    1.22 Gamma-ray pulsar binary search #1 on GPUs (FGRPopencl-intel_gpu)    LATeah3012L12221022_820.0_0_0.0_1667151_2    00:28:20 (00:28:10)    99,42        100,000    -    13d,21:57:40    1C + 1INT    Ready to report            A750    
 

Landjunge
Landjunge
Joined: 14 Oct 08
Posts: 4
Credit: 1149908448
RAC: 12274

Can you try running two tasks

Can you try running two tasks in parallel. Maybe it is scaling good.

Ian&Steve C.
Ian&Steve C.
Joined: 19 Jan 20
Posts: 3681
Credit: 33818304266
RAC: 37819403

yeah that's not too bad for

yeah that's not too bad for the FP32 part. not blazing fast, but decent for the power draw. that last 10% really kills it though for gamma ray.

it's unfortunate, because it would actually be pretty productive for gamma ray if it had any hw FP64 capability to get that last 10% done in a reasonable time.

and the credit reward for BRP4 is so low at just 62cr.

 

looking at about 100,000 ppd running BRP4

and about 165,000 ppd running FGRPB1G

_________________________________________________________________________

Ian&Steve C.
Ian&Steve C.
Joined: 19 Jan 20
Posts: 3681
Credit: 33818304266
RAC: 37819403

Landjunge wrote: Can you try

Landjunge wrote:

Can you try running two tasks in parallel. Maybe it is scaling good.

thats a good idea

_________________________________________________________________________

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.