• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Pixel Fillrate and Turing/Pascal

eraser666

New Member
Joined
Feb 7, 2019
Messages
15 (0.05/day)
Limited by GPC? the max Pixel Fillrate of TU106 is ROPs*frequency/4*3, the same as GP106(max Pixel Fillrate=ROPs*frequency/3*2).

You can use TU116(1660Ti,3GPC 48ROP) or TU106-200A(2060,3GPC 48ROP) comparing with TU104-400(2070,3GPC 64ROP) to verify this fact.

Remember! Use a same GPU and MEM frequency to verify this fact in Feature Test of 3DMark06 or 3DMark Vantage.

LOL!


QQ图片20190220143540.png
 
Last edited:
Joined
May 8, 2016
Messages
856 (0.67/day)
System Name BOX
Processor Xeon E5-1680 v2 @ 4,3GHz
Motherboard Sabertooth X79 (BIOS 4801 + NVMe mod + uCode update)
Cooling Thermalright Venomous-X (w/LGA 2011 kit) + 2x Delta PWM Push-Pull
Memory 8x A-Data Xtreme 2000X 2GB (1868MHz CL8.9.8.24 CR2T @ 1,65V)
Video Card(s) ASUS GTX 1080 (FE)
Storage Samsung SM961 256GB NVMe, RAID0 2x WD10EZEX (1TB), HGST HUS726060ALE610 (6TB)
Display(s) Samsung T240
Case NZXT Tempest (Nanoflux/PWM fans only, some w/LEDs)
Audio Device(s) ASUS Essence ST Deluxe 7.1
Power Supply Seasonic X-760 (760W)
Mouse Roccat Savu
Keyboard Logitech UltraXPremium
Software Windows 10 Pro x64
Benchmark Scores https://www.passmark.com/baselines/V9/display.php?id=108080818886

Pixel Fillrate = GPC count x 16 pixels x Core clock (close to max. Boost clock to be accurate).

Turing (overall) : If GPC x 16 > ROP, Pixel Fillrate = ROP x Core clock, else use GPC x 16.

Did I get it right ?
 

eraser666

New Member
Joined
Feb 7, 2019
Messages
15 (0.05/day)

Pixel Fillrate = GPC count x 16 pixels x Core clock (close to max. Boost clock to be accurate).

Turing (overall) : If GPC x 16 > ROP, Pixel Fillrate = ROP x Core clock, else use GPC x 16.

Did I get it right ?
Excellent!
 
Joined
May 8, 2016
Messages
856 (0.67/day)
System Name BOX
Processor Xeon E5-1680 v2 @ 4,3GHz
Motherboard Sabertooth X79 (BIOS 4801 + NVMe mod + uCode update)
Cooling Thermalright Venomous-X (w/LGA 2011 kit) + 2x Delta PWM Push-Pull
Memory 8x A-Data Xtreme 2000X 2GB (1868MHz CL8.9.8.24 CR2T @ 1,65V)
Video Card(s) ASUS GTX 1080 (FE)
Storage Samsung SM961 256GB NVMe, RAID0 2x WD10EZEX (1TB), HGST HUS726060ALE610 (6TB)
Display(s) Samsung T240
Case NZXT Tempest (Nanoflux/PWM fans only, some w/LEDs)
Audio Device(s) ASUS Essence ST Deluxe 7.1
Power Supply Seasonic X-760 (760W)
Mouse Roccat Savu
Keyboard Logitech UltraXPremium
Software Windows 10 Pro x64
Benchmark Scores https://www.passmark.com/baselines/V9/display.php?id=108080818886
You could say, those ROPs are there for "cheaper" Anti Aliasing ;)
Last time NV did this with Fermi (IIRC).
 
Joined
Jul 18, 2016
Messages
246 (0.20/day)
System Name Gaming PC / I7 XEON
Processor I7 4790K @stock / XEON W3680 @ stock
Motherboard Asus Z97 MAXIMUS VII FORMULA / GIGABYTE X58 UD7
Cooling X61 Kraken / X61 Kraken
Memory 32gb Vengeance 2133 Mhz / 24b Corsair XMS3 1600 Mhz
Video Card(s) Gainward GLH 1080 / MSI Gaming X Radeon RX480 8 GB
Storage Samsung EVO 850 500gb ,3 tb seagate, 2 samsung 1tb in raid 0 / Kingdian 240 gb, megaraid SAS 9341-8
Display(s) 2 BENQ 27" GL2706PQ / Dell UP2716D LCD Monitor 27 "
Case Corsair Graphite Series 780T / Corsair Obsidian 750 D
Audio Device(s) ON BOARD / ON BOARD
Power Supply Sapphire Pure 950w / Corsair RMI 750w
Mouse Steelseries Sesnsei / Steelseries Sensei raw
Keyboard Razer BlackWidow Chroma / Razer BlackWidow Chroma
Software Windows 1064bit PRO / Windows 1064bit PRO
GPU-Z show more Pixel Fillrate for those gpu?
 
Joined
Jun 3, 2010
Messages
452 (0.13/day)
I'm just talking about the pixel filling rate.

the display of gpu-z
It displayed wrong with GTX 970, too. TPU is used to such occurrances.

I mean it depends, anyway. I like the idea though, just as <99p testing we should have rasterizer performance information of individual scene setups like how much of an effect small & big triangles have.

How about a free licence of Beyond3D Suite as well, one cannot run short of such features. Though I doubt TPU has it, not having any associated publishings even after all these years.
 

eraser666

New Member
Joined
Feb 7, 2019
Messages
15 (0.05/day)
It displayed wrong with GTX 970, too. TPU is used to such occurrances.

I mean it depends, anyway. I like the idea though, just as <99p testing we should have rasterizer performance information of individual scene setups like how much of an effect small & big triangles have.

How about a free licence of Beyond3D Suite as well, one cannot run short of such features. Though I doubt TPU has it, not having any associated publishings even after all these years.
Thank you for your reply. According to feedback from B3D subscribers, there will be a public release version of Beyond 3D Suite in recent months, probably similar to that used by Anandtech.

GPU-Z show more Pixel Fillrate for those gpu?
I'm afraid so, including 1060, 1070, 2070, Quadro GV100 (Titan V JHH Special Edition), and maybe even 780.

https://www.anandtech.com/bench/GPU18/2347

:lovetpu:
 

eraser666

New Member
Joined
Feb 7, 2019
Messages
15 (0.05/day)
How about this formula?
pixel fillrate=min(ROP, GPC*16, TPC*4)*frequency/1000

For example:
they have the same pixel fillrate in test.
2070:3GPC/18TPC/64ROP 2060:3GPC/15TPC/48ROP 1660Ti:3GPC/12TPC/48ROP
1080:4GPC/20TPC/64ROP 1070Ti:4GPC/19TPC/64ROP

they have different pixel fillrate in test.
1080:4GPC/20TPC/64ROP 1070:3GPC/15TPC/64ROP
1060:2GPC/10TPC/48ROP 1050Ti:2GPC/6TPC/32ROP 1050:2GPC/5TPC/32ROP
 
Last edited:
Top