Jump to content

Fermi Compute

I am fascinated with Fermi for no good reason, maybe because of how much of a failure it was. Something I found interesting, was the exceptional compute, which was used for, you guessed it, Folding@home. In fact, when AnandTech did a review of the 580, they actually used Folding@home as a benchmark. My question is, would it be a good idea to buy several Fermi cards (GTX580s for about $60-$80 each), and set them up in a "mining" setup but for folding@home? From what I understand, mining takes a crazy amount of memory, and memory bandwidth, but how much is Folding@home dependant on those things? Would I be able to actually contribute anything worth the effort? (energy costs aren't really an issue)

Link to comment
Share on other sites

Link to post
Share on other sites

I found this database: https://folding.lar.systems/gpu_ppd/overall_ranks. It doesn't contain a GTX 580 unfortunately, but a GTX 570 HD. Compared to a current gen GPU it doesn't look too good.

RTX 3090    – 7,493,734 PPD
GTX 1080 Ti – 2,416,910 PPD
AMD RX 480  –   448,477 PPD
GTX 570 HD  –    63,361 PPD

You'd need roughly 118 GTX 570s to match a single RTX 3090 or 38 to match a single GTX 1080 Ti. So in terms of perf/watt or perf/$ you're much better off with a modern GPU.

 

If you can get each card at an average of $70, you'd be paying ~$8,260 to match the performance of a RTX 3090 and still $2,660 to match the performance of a 1080 Ti.

 

Of course any contribution helps. Every WU completed adds to the total number of WUs solved per hour/day/year 😉

Remember to either quote or @mention others, so they are notified of your reply

Link to comment
Share on other sites

Link to post
Share on other sites

Fermi was great, but god damn they were noisy, hot GPU’s that performed well (at the time). I remember owning a GTX 470 and it did the trick, but even with a aftermarket design/heatsink that GPU was a hot little oven that could cook an egg in < 2 seconds lol.

Case: Fractal Define R6 USB-C Tempered Glass CPU: Ryzen 9 7950X @ 4.5GHz Motherboard: ASUS X670E ROG Crosshair Hero RAM: 32GB DDR5 6600MHz G.Skill GPU: ASUS RTX 4090 ROG Strix OC PSU: Seasonic TX1600W 80+ Titanium Drives: 500GB SSD (2x), 1TB SSD (2X), 960GB SSD, 2TB SSD, 2TB HDD Display: Samsung Odyssey Neo G8 (32", 2160p 240Hz, G-Sync, HDR 1000+)

Link to comment
Share on other sites

Link to post
Share on other sites

Folding has a higher demand on PCIe bandwidth to keep the GPU occupied with scientific data to crunch. You cannot expect the cards to perform at their best when you have them on the 1x risers like in a mining setup.

 

Heck, I would predict if they are on the 1x risers, they might not be able to get to 100% utilization, thus not get too hot. 🙂

CPU Intel Xeon X5650 | Cooling Corsair H80i GT | Motherboard ASUS Sabretooth X58 | RAM Corsair Vengeance 1.6GHz 9-9-9-24 24GB | GPU EVGA GeForce RTX 3070 FTW3 Ultra Gaming | Case Fractal Design Define R5 |

Storage Samsung 860 Pro 512GB, Samsung 850 EVO 500GB, WD Black 640GB, WD Green 4TB, WD Blue 4TB | PSU Corsair TX750 "v1" | Display ASUS VP247QG + Samsung SyncMaster T220

Link to comment
Share on other sites

Link to post
Share on other sites

On 12/17/2021 at 1:29 PM, Eigenvektor said:

I found this database: https://folding.lar.systems/gpu_ppd/overall_ranks. It doesn't contain a GTX 580 unfortunately, but a GTX 570 HD. Compared to a current gen GPU it doesn't look too good.

RTX 3090    – 7,493,734 PPD
GTX 1080 Ti – 2,416,910 PPD
AMD RX 480  –   448,477 PPD
GTX 570 HD  –    63,361 PPD

You'd need roughly 118 GTX 570s to match a single RTX 3090 or 38 to match a single GTX 1080 Ti. So in terms of perf/watt or perf/$ you're much better off with a modern GPU.

 

If you can get each card at an average of $70, you'd be paying ~$8,260 to match the performance of a RTX 3090 and still $2,660 to match the performance of a 1080 Ti.

 

Of course any contribution helps. Every WU completed adds to the total number of WUs solved per hour/day/year 😉

Here is an older sheet with performance figures for Fermi. So 39,000 to 43,000 PPD for a 570 or 580 or less than a 3600 CPU these days. Likely if they were supported you'd get 45 - 50kPPD with CUDA improvements.

 

These are only PCIe Gen 2 cards as well so on a PCIe2x1 riser you'd get half the bandwidth as a Gen3 so even worse.

FaH BOINC HfM

Bifrost - 6 GPU Folding Rig  Linux Folding HOWTO Folding Remote Access Folding GPU Profiling

Systems:

desktop: Lian-Li O11 Air Mini; Gigabyte Aorus ax570 Master; Ryzen 9 5900x;Noctua NH-D15; 4 x 16GB DDR4-3200; 500GB PCIe3 NVMe; 4 x 3TB NAS; AMD RadeonPro W4100; EVGA RTX 2060 XC Ultra Gaming; Corsair TX650M

nas1: Fractal Define R4; SuperMicro X10sl7-f; Xeon e3-1231v3; 4 x 8GB DDR3-1666 ECC; 6 x 3TB NAS; 6 x 4TB NAS

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

dcn01: Fractal Meshify C; Gigabyte Aorus ax570 Master; Ryzen 9 5950x; EVGA 240 CLC; 2 x 32GB DDR4-3200; 512GB NVMe; EVGA RTX 2070 Super XC Hybrid; EVGA RTX 3070 XC Ultra; Corsair TX650M

dcn02: Fractal Define S; Gigabyte ax570 Pro WiFi; Ryzen 9 3950x; Noctua NH-D15; 2 x 16GB DDR4-3200; 128GB NVMe; EVGA RTX 2070 Super XC Hybrid; EVGA RTX3080 FTW3; Corsair RM750x

dcn03: Fractal Meshify S2; Gigabyte Aorus ax570 Pro WiFi; Ryzen 9 5900x; Noctua NH-U12S; 2 x 16GB DDR4-3200; 128GB NVMe; EVGA RTX 2070 Super XC Hybrid; EVGA RTX 3080 XC Ultra; Corsair RM750

dcn04: Fractal Meshify S2; Gigabyte x370 Gaming K7; Ryzen 9 3900x; Noctua NH-U12S; 4 x 16GB DDR4-3200; 128GB NVMe; EVGA RTX 2070 Super XC Hybrid; Asus TUF RTX3070 ti; Corsair TX750M

dcn05: Fractal Define R4; Gigabyte ax370 Gaming K7; i9-9900K; EVGA 280 CLC; 2 x 8GB DDR4-3200; 128GB NVMe; EVGA RTX 2070 Super XC Hybrid; EVGA RTX 3080 XC Ultra; Corsair TX650M

dcn10: Fractal Define C; Gigabyte Aorus x570 Gaming X; Ryzen 7 2700x; Hyper 212Evo e/w Noctua NF-A12 iPPC2000; 2 x 8GB DDR4-3200; Samsung 250GB SSD; EVGA RTX 2070A; EVGA RTX 2060 Super XC Gaming; Corsair CX650M Bronze

dcn11: Fractal Focus G mini; Gigabyte b450 Aorus M; Aorus M; Ryzen 7 2700; Wraith Spire; 2 x 8GB DDR4-3200; Samsung 840 Pro 128GB SSD; EVGA XC GTX 1070 ti 8GB; Corsair CX450M Bronze

dcn12: Fractal Core 1100; Gigabyte b450 Aorus M; Ryzen 7 2700; Wraith Spire; 2 x 8GB DDR4-3200; Samsung EVO 850 128GB SSD; EVGA GTX 1660ti XC Ultra Gaming; Corsair TX550M Bronze

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


×