Jump to content

Anyone else notice this?

drewdsterling
 Share
Posted

Hey everyone!

I am folding on my gpu and cpu, I noticed that the cpu workloads are saying that they are AVX_256 in the log sometimes.  I noticed that a 1,000,000 step workload on the cpu with the AVX_256 workloads are sometimes faster than my gpu workloads with the same 1,000,000 step core.  Can someone explain why this is?  I tried looking for an explanation online but got a lot of nothing, hoping someone here can enlighten me!

Thank you!! 

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
1 hour ago, drewdsterling said:

Hey everyone!

I am folding on my gpu and cpu, I noticed that the cpu workloads are saying that they are AVX_256 in the log sometimes.  I noticed that a 1,000,000 step workload on the cpu with the AVX_256 workloads are sometimes faster than my gpu workloads with the same 1,000,000 step core.  Can someone explain why this is?  I tried looking for an explanation online but got a lot of nothing, hoping someone here can enlighten me!

Thank you!! 

Can you post a copy of your logs and specs?

COMMUNITY STANDARDS   |   TECH NEWS POSTING GUIDELINES   |   FORUM STAFF

LTT Folding Users Tips, Tricks and FAQ   |   F@H & BOINC Badge Request   |   F@H Contribution   |   My Rig   |   Project Steamroller

I am a Moderator, but I am fallible. Discuss or debate with me as you will but please do not argue with me as that will get us nowhere.

 

Spoiler

† † †

 

Character is like a Tree and Reputation like its Shadow. The Shadow is what we think of it; The Tree is the Real thing.  ~ Abraham Lincoln

Reputation is a Lifetime to create but seconds to destroy.

You have enemies? Good. That means you've stood up for something, sometime in your life.  ~ Winston Churchill

Docendo discimus - "to teach is to learn"

 

† CHRISTIAN MEMBER †

 

 
 
 
 
 
 

 

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
  • Author
3 hours ago, SansVarnic said:

Can you post a copy of your logs and specs?

Yes I can, I turned it off for the night but I will tomorrow 

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
  • Author
On 3/29/2020 at 8:03 PM, SansVarnic said:

Can you post a copy of your logs and specs?

Sorry I could not get it to replicate for a while until now.  So where it says build is where in this project description it says "avx_256".  So what I am confused on is how my CPU when using this AVX-256 project is faster than my GPU with a similar amount of points workload? Is 1 CPU step not the same to 1 GPU step? Or is there something else going on?

Log Copy

19:46:53:WU01:FS00:0xa7:*********************** Log Started 2020-04-03T19:46:53Z ***********************
19:46:53:WU01:FS00:0xa7:************************** Gromacs Folding@home Core ***************************
19:46:53:WU01:FS00:0xa7:       Type: 0xa7
19:46:53:WU01:FS00:0xa7:       Core: Gromacs
19:46:53:WU01:FS00:0xa7:       Args: -dir 01 -suffix 01 -version 705 -lifeline 12164 -checkpoint 3 -np
19:46:53:WU01:FS00:0xa7:             10
19:46:53:WU01:FS00:0xa7:************************************ CBang *************************************
19:46:53:WU01:FS00:0xa7:       Date: Oct 26 2019
19:46:53:WU01:FS00:0xa7:       Time: 01:38:25
19:46:53:WU01:FS00:0xa7:   Revision: c46a1a011a24143739ac7218c5a435f66777f62f
19:46:53:WU01:FS00:0xa7:     Branch: master
19:46:53:WU01:FS00:0xa7:   Compiler: Visual C++ 2008
19:46:53:WU01:FS00:0xa7:    Options: /TP /nologo /EHa /wd4297 /wd4103 /Ox /MT
19:46:53:WU01:FS00:0xa7:   Platform: win32 10
19:46:53:WU01:FS00:0xa7:       Bits: 64
19:46:53:WU01:FS00:0xa7:       Mode: Release
19:46:53:WU01:FS00:0xa7:************************************ System ************************************
19:46:53:WU01:FS00:0xa7:        CPU: Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz
19:46:53:WU01:FS00:0xa7:     CPU ID: GenuineIntel Family 6 Model 158 Stepping 10
19:46:53:WU01:FS00:0xa7:       CPUs: 12
19:46:53:WU01:FS00:0xa7:     Memory: 31.86GiB
19:46:53:WU01:FS00:0xa7:Free Memory: 26.60GiB
19:46:53:WU01:FS00:0xa7:    Threads: WINDOWS_THREADS
19:46:53:WU01:FS00:0xa7: OS Version: 6.2
19:46:53:WU01:FS00:0xa7:Has Battery: false
19:46:53:WU01:FS00:0xa7: On Battery: false
19:46:53:WU01:FS00:0xa7: UTC Offset: -7
19:46:53:WU01:FS00:0xa7:        PID: 14392
19:46:53:WU01:FS00:0xa7:        CWD: C:\Users\drewd\AppData\Roaming\FAHClient\work
19:46:53:WU01:FS00:0xa7:******************************** Build - libFAH ********************************
19:46:53:WU01:FS00:0xa7:    Version: 0.0.18
19:46:53:WU01:FS00:0xa7:     Author: Joseph Coffland <joseph@cauldrondevelopment.com>
19:46:53:WU01:FS00:0xa7:  Copyright: 2019 foldingathome.org
19:46:53:WU01:FS00:0xa7:   Homepage: https://foldingathome.org/
19:46:53:WU01:FS00:0xa7:       Date: Oct 26 2019
19:46:53:WU01:FS00:0xa7:       Time: 01:52:30
19:46:53:WU01:FS00:0xa7:   Revision: c1e3513b1bc0c16013668f2173ee969e5995b38e
19:46:53:WU01:FS00:0xa7:     Branch: master
19:46:53:WU01:FS00:0xa7:   Compiler: Visual C++ 2008
19:46:53:WU01:FS00:0xa7:    Options: /TP /nologo /EHa /wd4297 /wd4103 /Ox /MT
19:46:53:WU01:FS00:0xa7:   Platform: win32 10
19:46:53:WU01:FS00:0xa7:       Bits: 64
19:46:53:WU01:FS00:0xa7:       Mode: Release
19:46:53:WU01:FS00:0xa7:************************************ Build *************************************
19:46:53:WU01:FS00:0xa7:       SIMD: avx_256
19:46:53:WU01:FS00:0xa7:********************************************************************************
19:46:53:WU01:FS00:0xa7:Project: 14364 (Run 196, Clone 1, Gen 11)
19:46:53:WU01:FS00:0xa7:Unit: 0x0000000d9bf7a4d65e7cbfc4870ec8dd
19:46:53:WU01:FS00:0xa7:Reading tar file core.xml
19:46:53:WU01:FS00:0xa7:Reading tar file frame11.tpr
19:46:53:WU01:FS00:0xa7:Digital signatures verified
19:46:53:WU01:FS00:0xa7:Calling: mdrun -s frame11.tpr -o frame11.trr -cpt 3 -nt 10
19:46:53:WU01:FS00:0xa7:Steps: first=0 total=2500000
19:46:54:WU01:FS00:0xa7:Completed 1 out of 2500000 steps (0%)
19:47:23:WU00:FS01:0x22:Completed 10000 out of 1000000 steps (1%) -GPU
19:48:03:WU01:FS00:0xa7:Completed 25000 out of 2500000 steps (1%) -CPU
19:48:30:WU00:FS01:0x22:Completed 20000 out of 1000000 steps (2%) -GPU
19:49:14:WU01:FS00:0xa7:Completed 50000 out of 2500000 steps (2%) -CPU
19:49:38:WU00:FS01:0x22:Completed 30000 out of 1000000 steps (3%) -GPU
19:50:26:WU01:FS00:0xa7:Completed 75000 out of 2500000 steps (3%)
19:50:45:WU00:FS01:0x22:Completed 40000 out of 1000000 steps (4%)
19:51:30:WU01:FS00:0xa7:Completed 100000 out of 2500000 steps (4%)
19:51:53:WU00:FS01:0x22:Completed 50000 out of 1000000 steps (5%)
19:52:34:WU01:FS00:0xa7:Completed 125000 out of 2500000 steps (5%)
19:53:06:WU00:FS01:0x22:Completed 60000 out of 1000000 steps (6%)
19:53:34:WU01:FS00:0xa7:Completed 150000 out of 2500000 steps (6%)
19:54:13:WU00:FS01:0x22:Completed 70000 out of 1000000 steps (7%)
19:54:31:WU01:FS00:0xa7:Completed 175000 out of 2500000 steps (7%)
19:55:20:WU00:FS01:0x22:Completed 80000 out of 1000000 steps (8%)
19:55:31:WU01:FS00:0xa7:Completed 200000 out of 2500000 steps (8%)
19:56:28:WU00:FS01:0x22:Completed 90000 out of 1000000 steps (9%)
19:56:37:WU01:FS00:0xa7:Completed 225000 out of 2500000 steps (9%)
19:57:35:WU00:FS01:0x22:Completed 100000 out of 1000000 steps (10%)
19:57:42:WU01:FS00:0xa7:Completed 250000 out of 2500000 steps (10%)
19:58:44:WU01:FS00:0xa7:Completed 275000 out of 2500000 steps (11%)
19:58:47:WU00:FS01:0x22:Completed 110000 out of 1000000 steps (11%)
19:59:45:WU01:FS00:0xa7:Completed 300000 out of 2500000 steps (12%)
19:59:55:WU00:FS01:0x22:Completed 120000 out of 1000000 steps (12%)
20:00:48:WU01:FS00:0xa7:Completed 325000 out of 2500000 steps (13%)
20:01:02:WU00:FS01:0x22:Completed 130000 out of 1000000 steps (13%)
20:01:53:WU01:FS00:0xa7:Completed 350000 out of 2500000 steps (14%)
20:02:09:WU00:FS01:0x22:Completed 140000 out of 1000000 steps (14%)
20:03:04:WU01:FS00:0xa7:Completed 375000 out of 2500000 steps (15%)
20:03:17:WU00:FS01:0x22:Completed 150000 out of 1000000 steps (15%)
20:04:12:WU01:FS00:0xa7:Completed 400000 out of 2500000 steps (16%)
20:04:28:WU00:FS01:0x22:Completed 160000 out of 1000000 steps (16%)
20:05:18:WU01:FS00:0xa7:Completed 425000 out of 2500000 steps (17%)
20:05:36:WU00:FS01:0x22:Completed 170000 out of 1000000 steps (17%)
20:06:20:WU01:FS00:0xa7:Completed 450000 out of 2500000 steps (18%)
20:06:43:WU00:FS01:0x22:Completed 180000 out of 1000000 steps (18%)
20:07:20:WU01:FS00:0xa7:Completed 475000 out of 2500000 steps (19%)
20:07:51:WU00:FS01:0x22:Completed 190000 out of 1000000 steps (19%)
20:08:25:WU01:FS00:0xa7:Completed 500000 out of 2500000 steps (20%)
20:08:58:WU00:FS01:0x22:Completed 200000 out of 1000000 steps (20%)

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
  • Author
On 3/29/2020 at 8:03 PM, SansVarnic said:

Can you post a copy of your logs and specs?

CPU 8700K

GPU 1070TI

Memory 32GBs 3200MHzs

Link to comment
Share on other sites
Link to post
Share on other sites
Posted

You will never get the same Work Unit (WU) on a CPU and GPU so you really can't compare them. GPU WUs are preferred due to their massively parallel architecture but they are limited in the types of Math operations they can do. More complex operations have to use CPU WUs.

FaH BOINC HfM

Bifrost - 6 GPU Folding Rig  Linux Folding HOWTO Folding Remote Access Folding GPU Profiling ToU Scheduling UPS

Systems:

desktop: Lian-Li O11 Air Mini; Asus ProArt x670 WiFi; Ryzen 9 7950x; EVGA 240 CLC; 4 x 32GB DDR5-5600; 2 x Samsung 980 Pro 500GB PCIe3 NVMe; 2 x 8TB NAS; AMD FirePro W4100; MSI 4070 Ti Super Ventus 2; Corsair SF750

nas1: Fractal Node 804; SuperMicro X10sl7-f; Xeon e3-1231v3; 4 x 8GB DDR3-1666 ECC; 2 x 250GB Samsung EVO Pro SSD; 7 x 4TB Seagate NAS; Corsair HX650i

nas2: Synology DS-123j; 2 x 6TB WD Red Plus NAS

nas3: Synology DS-224+; 2 x 12TB Seagate NAS

dcn01: Fractal Meshify S2; Gigabyte Aorus ax570 Master; Ryzen 9 5900x; Noctua NH-D15; 4 x 16GB DDR4-3200; 512GB NVMe; 2 x Zotac AMP 4070ti; Corsair RM750Mx

dcn02: Fractal Meshify S2; Gigabyte ax570 Pro WiFi; Ryzen 9 3950x; Noctua NH-D15; 2 x 16GB DDR4-3200; 128GB NVMe; 2 x Zotac AMP 4070ti; Corsair RM750x

dcn03: Fractal Meshify C; Gigabyte Aorus z370 Gaming 5; i9-9900k; BeQuiet! PureRock 2 Black; 2 x 8GB DDR4-2400; 128GB SATA m.2; MSI 4070 Ti Super Gaming X; MSI 4070 Ti Super Ventus 2; Corsair TX650m

dcn05: Fractal Define S; Gigabyte Aorus b450m; Ryzen 7 2700; AMD Wraith; 2 x 8GB DDR 4-3200; 128GB SATA NVMe; Gigabyte Gaming RTX 4080 Super; Corsair TX750m

dcn06: Fractal Focus G Mini; Gigabyte Aorus b450m; Ryzen 7 2700; AMD Wraith; 2 x 8GB DDR 4-3200; 128GB SSD; Gigabyte Gaming RTX 4080 Super; Corsair CX650m

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
  • Author
55 minutes ago, Gorgon said:

You will never get the same Work Unit (WU) on a CPU and GPU so you really can't compare them. GPU WUs are preferred due to their massively parallel architecture but they are limited in the types of Math operations they can do. More complex operations have to use CPU WUs.

Oh gotcha so steps do not matter and do not compare, thank you for your help with this.  I was just amazed by the steps haha. Thank you again!

Link to comment
Share on other sites
Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
 Share
Go to topic listing Folding@home, Boinc, and Coin Mining

×