mersenneforum.org  

Go Back   mersenneforum.org > Search Forums

Showing results 1 to 9 of 9
Search took 0.00 seconds.
Search: Posts Made By: frmky
Forum: Msieve 2021-08-07, 02:20
Replies: 46
Views: 24,628
Posted By frmky
No, VBITS is the number of bits in each vector...

No, VBITS is the number of bits in each vector entry used in the block Lanczos iteration. It's adjustable at compile time to be 64, 128, or 256 (or 512 in my hosted version). In the code, it's...
Forum: Msieve 2021-07-30, 21:56
Replies: 46
Views: 24,628
Posted By frmky
After reimplementing the CUDA SpMV with CUB, the...

After reimplementing the CUDA SpMV with CUB, the Tesla V100 now takes 36 minutes.
Forum: Msieve 2021-05-12, 18:47
Replies: 46
Views: 24,628
Posted By frmky
Set the cache size in the source, optionally...

Set the cache size in the source, optionally remove the loop unrolling, set the optimization flags for the machine in Makefile (really just -Ofast -mcpu=native is usually fine) and compile. In the...
Forum: Msieve 2021-05-10, 04:38
Replies: 46
Views: 24,628
Posted By frmky
nVidia Tesla V100 with now old CUDA code that...

nVidia Tesla V100 with now old CUDA code that only supports 64-bit vectors
1h 26m
53 minutes after many code changes.
Forum: Msieve 2021-05-09, 22:24
Replies: 46
Views: 24,628
Posted By frmky
One node with 2 x Cavium ThunderX2 CN9980 32-core...

One node with 2 x Cavium ThunderX2 CN9980 32-core 64-bit ARM cpus and DDR4 memory.

VBITS = 64 2h 57m
VBITS = 128 2h 1m
VBITS = 256 2h 2m
Forum: Msieve 2021-05-09, 20:16
Replies: 46
Views: 24,628
Posted By frmky
common/lanczos/cpu/lanczos_cpu.h:#define...

common/lanczos/cpu/lanczos_cpu.h:#define MAX_THREADS 32
Forum: Msieve 2021-05-09, 08:57
Replies: 46
Views: 24,628
Posted By frmky
Each node has a Fujitsu A64FX 64-bit ARM...

Each node has a Fujitsu A64FX 64-bit ARM processor with 48 cores and 32 GB HBM memory divided into 4 NUMA regions.

VBITS = 128
1 node 3h 30m
2 nodes 1h 58m
4 nodes 1h 10m
8 nodes 0h 41m
...
Forum: Msieve 2020-08-15, 07:23
Replies: 46
Views: 24,628
Posted By frmky
Here's a bench using compute nodes with one Xeon...

Here's a bench using compute nodes with one Xeon E5-2650 v4 Broadwell cpu with 12-cores, 24 threads.

1 node 7h 40m
2 nodes 2h 45m
4 nodes 1h 35m
8 nodes 1h 10m

Not sure why the time for...
Forum: Msieve 2020-08-14, 18:06
Replies: 46
Views: 24,628
Posted By frmky
I know this is late, but if you still have this...

I know this is late, but if you still have this data set up, try
mpirun -np 2 msieve -nc2 1,2 -v -t 20
Showing results 1 to 9 of 9

 
All times are UTC. The time now is 18:29.


Tue Dec 7 18:29:12 UTC 2021 up 137 days, 12:58, 2 users, load averages: 1.06, 1.46, 1.49

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.