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

VRAM frequency vs. Latency

Win_Wiz

New Member
Joined
Oct 11, 2018
Messages
11 (0.06/day)
Likes
4
#1
Anyone knows if games generally favors high frequency over low latency VRAM?
I'm asking because I modified the bios on my Rx 580 to use the 1900MHz memory strap above 2000MHz. Before the bios mod I clocked the Vram @2400MHz, after the mod Max is about 2150MHz but my 3Dmark score increased. So I'm wondering if games also prefer low latency VRAM, but I don't have any games with reliable benchmarks. Searching Google only displays results related to mining or regular system RAM. But I read somewhere that graphics is all about bandwidth (MHz) but this was related to integrated graphics, so I don't know if dedicated graphics also prefer high frequency.
I'm guessing it's probably a balance between frequency and timings but would like to know.
 
Joined
Jun 15, 2016
Messages
962 (0.92/day)
Likes
474
System Name My PC
Processor 4670K@4.4GHz
Motherboard Gryphon Z87
Cooling CM 212
Memory 2x8GB+2x4GB @2400GHz
Video Card(s) XFX Radeon RX 580 GTS Black Edition 1425MHz OC+, 8GB
Storage Intel 530 SSD 480GB + Intel 510 SSD 120GB + 2x500GB hdd raid 1
Display(s) HP envy 32 1440p
Case CM Mastercase 5
Audio Device(s) Sbz Zxr
Power Supply Antec 620W
Mouse G502
Keyboard G910
Software Win 10 pro
#2
Balance is the key here leave it @2000MHz
 
Joined
May 8, 2016
Messages
778 (0.72/day)
Likes
941
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
#3
It's usefull to have both.
They simply come to play at different times (and actual gain from either, depends on gpu architecture).
Short version :
Bandwidth is needed always (because creating pixels is VERY data manipulation intensive and it has to go/come from somewhere).
If GPU has the compute power, bandwidth is essencial to keep it "fed" and operate at peak values.
Latency on the other hand is good to have for efficient use of GPUs power (less time it takes to deliver new data, the faster work can start on it).
But getting large ammounts of data at the quickest time isn't easy.
That's why most newer GPUs "hide" latency behind complex instructions (for data already operated on), and large caches.
It gives memory/IMC time to deliver the next batch for processing.

GTX 1070 Ti vs. GTX 1080 is great example of this.
G5 VRAM on former has tighter latency, while G5X VRAM on latter has higher bandwidth throughput.
Still, it's a Pascal example, while you own GCN.
 
Last edited:

Win_Wiz

New Member
Joined
Oct 11, 2018
Messages
11 (0.06/day)
Likes
4
#4
Forgot to mention my Rx 580 is the 4GB version so default ram frequency is only 1750.
Kastriot: Why do you think 2000MHz is faster than 2150MHz, do you mean I should find the lowest memory strap that's stable @2GHz?
 
Joined
Apr 5, 2015
Messages
17 (0.01/day)
Likes
7
System Name AMD ITX
Processor Athlon 5350@2.3GHz 1.3v
Motherboard AsRock AM1H-ITX
Cooling Artic Cooling AM1 Passive
Memory 8GB Samsung LP@1900MHz 1.65v
Storage 1TB WD Black 3.5" HDD + 750GB 2.5" HDD
Display(s) Lenovo 22" 16:10 1680x1050
Case Cooltek ITX Mini Cube
Audio Device(s) Scythe SDA-2100 + Passive Stereo Speakers
Power Supply 19v ASUS PowerBrick
Software openSUSE Tumbleweed
#5
High memory clock is always good, we need as much maximum bandwidth as possible, but because of the Architecture + IMC + messy/bad Timings the real bandwith is lower, keepeing the memory at a high-but-not-to-high frequency + reduced comunication / roundtrip latencies can be more effective in the real world and produce more performance (try OCLMembench or AIDA64). Polaris memory more or less always clock around 2.1-2.2Ghz (the gpu is designed for 2Ghz, even the new RX590 use 2(8)Ghz GDDR5,or maybe is just a cost saving thing, the IMC@12nm should support 9Ghz vram ), give the memory good timings and it will work great. I don't like the Low latency vs High frequency argument, High clock + decent timings give the best results most of the time .The real latency in ns for any memory operation depend from single timing (in clock cycles) but also from the clock cycle speed (frequency). You need to find the best combination for your gpu/memory chip. Just my two cents here
 
Joined
May 12, 2017
Messages
341 (0.48/day)
Likes
137
#6
Last edited:
Joined
Jan 8, 2017
Messages
3,991 (4.76/day)
Likes
3,106
System Name Good enough
Processor AMD Ryzen R7 1700X - 4.0 Ghz / 1.350V
Motherboard ASRock B450M Pro4
Cooling Scythe Katana 4 - 3x 120mm case fans
Memory 16GB - Corsair Vengeance LPX
Video Card(s) OEM Dell GTX 1080
Storage 1x Samsung 850 EVO 250GB , 1x Samsung 860 EVO 500GB
Display(s) 4K Samsung TV
Case Zalman R1
Power Supply 500W
#7
Joined
May 12, 2017
Messages
341 (0.48/day)
Likes
137
#8
Memory bandwidth matters a lot for GPU architectures.



He is talking about VRAM.
I just edited my last post. Latency is still important, as it is still a unwanted delay. Can someone please post a BIOS timings of a GFX card memory timings.

I think such a screenshot will be useful for this thread.
 
Joined
Apr 5, 2015
Messages
17 (0.01/day)
Likes
7
System Name AMD ITX
Processor Athlon 5350@2.3GHz 1.3v
Motherboard AsRock AM1H-ITX
Cooling Artic Cooling AM1 Passive
Memory 8GB Samsung LP@1900MHz 1.65v
Storage 1TB WD Black 3.5" HDD + 750GB 2.5" HDD
Display(s) Lenovo 22" 16:10 1680x1050
Case Cooltek ITX Mini Cube
Audio Device(s) Scythe SDA-2100 + Passive Stereo Speakers
Power Supply 19v ASUS PowerBrick
Software openSUSE Tumbleweed
#9
https://www.techpowerup.com/vgabios/184585/xfx-rx480-8192-160615
Memory Timings (Samsung) tRCDW-tRCDWA-tRCDR-tRCDRA-tRC-tCL-tRFC
250 MHz: 2-3-3-3-11-8-27
400 MHz: 3-3-5-5-17-9-43
600 MHz: 5-5-8-8-26-11-65
900 MHz: 7-7-13-13-39-15-98
1000 MHz: 8-8-14-14-43-16-109
1125 MHz: 9-9-16-16-49-17-123
1250 MHz: 10-10-18-18-55-18-137
1375 MHz: 12-12-20-20-61-19-151
1500 MHz: 13-13-22-22-65-20-164
1625 MHz: 14-14-24-24-71-21-178
1750 MHz: 16-16-26-26-77-22-192
2000 MHz: 17-17-29-29-87-24-219

Overall between the two, latency wins. To give you an idea try this link for DDR memory (fill-in yellow boxes only) & pay particular attention to the eight word (far right column).

https://docs.google.com/spreadsheet...mV_44QazuvsSjjTu-H4KyVfpg/edit#gid=2008389493

EDIT: Please do not fill this thread with DDR Memory comments, as this thread is about "VRAM". Start a new thread about DDR timing vs frequency.
We do not have dividers/multipliers for memory clock in GPUs, we have the freedom to use every latency/clock combination we want. With CPUs you need to choose a frequency strap and than use certain timings that works << some combinations are better than others.
What if we take the DDR4-3600@CL16 and we OC the memory to lets say 3700Mhz?(if the IMC is not holding us back)

also (testing the spreadsheet), a "fake" DDR4-8000@CL24 is faster (latency and bandwidth) than a DDR4-7000@CL22 that is faster than DDR4-6500@CL21. I'm pretty sure GDDR5 behave a little different than DDR4 at high clocks, but the idea and results are probably the same or at least comparable.
 
Last edited:
Joined
May 12, 2017
Messages
341 (0.48/day)
Likes
137
#10
https://www.techpowerup.com/vgabios/184585/xfx-rx480-8192-160615
Memory Timings (Samsung) tRCDW-tRCDWA-tRCDR-tRCDRA-tRC-tCL-tRFC
250 MHz: 2-3-3-3-11-8-27
400 MHz: 3-3-5-5-17-9-43
600 MHz: 5-5-8-8-26-11-65
900 MHz: 7-7-13-13-39-15-98
1000 MHz: 8-8-14-14-43-16-109
1125 MHz: 9-9-16-16-49-17-123
1250 MHz: 10-10-18-18-55-18-137
1375 MHz: 12-12-20-20-61-19-151
1500 MHz: 13-13-22-22-65-20-164
1625 MHz: 14-14-24-24-71-21-178
1750 MHz: 16-16-26-26-77-22-192
2000 MHz: 17-17-29-29-87-24-219
Thanks. It's not often you see this. My opinion on this is to up the frequency their increased the timings. This is something I don't like when you get near the top-end frequency. ie I would have like to see @1500MHz it says the same all the way to 2000MHz.

What it does show is that the controller is capable of tight timings. This is what I would adjust, because at higher resolution you should get smoother game-play (less stuttering).


EDIT: You need to start a new thread for standard DDRx comments.
 
Last edited:
Joined
Apr 5, 2015
Messages
17 (0.01/day)
Likes
7
System Name AMD ITX
Processor Athlon 5350@2.3GHz 1.3v
Motherboard AsRock AM1H-ITX
Cooling Artic Cooling AM1 Passive
Memory 8GB Samsung LP@1900MHz 1.65v
Storage 1TB WD Black 3.5" HDD + 750GB 2.5" HDD
Display(s) Lenovo 22" 16:10 1680x1050
Case Cooltek ITX Mini Cube
Audio Device(s) Scythe SDA-2100 + Passive Stereo Speakers
Power Supply 19v ASUS PowerBrick
Software openSUSE Tumbleweed
#11
Thanks. It's not often you see this. My opinion on this is to up the frequency their increased the timings. This is something I don't like when you get near the top-end frequency. ie I would have like to see @1500MHz it says the same all the way to 2000MHz.

What it does show is that the controller is capable of tight timings. This is what I would adjust, because at higher resolution you should get smoother game-play (less stuttering).
https://www.overclock.net/forum/67-amd/1604567-polaris-bios-editing-rx5xx-rx4xx.html
check the "Memory Overclock - Scaling - Errors monitoring " section.
The user "-Loladinas- " made a test from 2000Mhz to 2250Mhz, Stock vs (My)UberMix v3.1 timings.
UberMix v3.1 are a 1500 - 1625 - 2000 straps Mix.
On Polaris the last strap is 2000Mhz, so after that "all" remain the same, no steps from there.

EDIT1:
Another thing here:
https://www.techpowerup.com/forums/threads/gddr5-oc-performance-scaling.218441/
Look at the 1250Mhz strap applying the new timings

EDIT2:
it is really difficult to separate the "latency" effect from the "real bandwith" effect

EDIT3:
EDIT: You need to start a new thread for standard DDRx comments.
i was "faking" a GDDR5 8Ghz with the spreadsheet, i'm not talking about DDR4 System Memory. I was using that to prove my point.

EDIT4... again:
Look at Nvidia, when they want to increase the compute power, they increase the local GPU Cache (https://www.anandtech.com/show/13004/nvidia-limited-edition-32gb-titan-v-ceo-edition) 6MB vs 4.5MB. To gain performance in games they use memory compression, to save bandwidth.
Just thinking...
 
Last edited:
Joined
May 12, 2017
Messages
341 (0.48/day)
Likes
137
#12
https://www.overclock.net/forum/67-amd/1604567-polaris-bios-editing-rx5xx-rx4xx.html
check the "Memory Overclock - Scaling - Errors monitoring " section.
The user "-Loladinas- " made a test from 2000Mhz to 2250Mhz, Stock vs (My)UberMix v3.1 timings.
UberMix v3.1 are a 1500 - 1625 - 2000 straps Mix.
On Polaris the last strap is 2000Mhz, so after that "all" remain the same, no steps from there.

Another thing here:
https://www.techpowerup.com/forums/threads/gddr5-oc-performance-scaling.218441/
Look at the 1250Mhz strap applying the new timings

it is really difficult to separate the "latency" effect from the "real bandwith" effect


i was "faking" a GDDR5 8Ghz with the spreadsheet, i'm not talking about DDR4 System Memory. I was using that to prove my point.

What's is tRCDWA & tRCDRA? I know what the others are.

Time/Row/Column/Delay/?/?

EDIT: I take it W=Write & R=Read but what is "A"?
 
Last edited:
Joined
Apr 5, 2015
Messages
17 (0.01/day)
Likes
7
System Name AMD ITX
Processor Athlon 5350@2.3GHz 1.3v
Motherboard AsRock AM1H-ITX
Cooling Artic Cooling AM1 Passive
Memory 8GB Samsung LP@1900MHz 1.65v
Storage 1TB WD Black 3.5" HDD + 750GB 2.5" HDD
Display(s) Lenovo 22" 16:10 1680x1050
Case Cooltek ITX Mini Cube
Audio Device(s) Scythe SDA-2100 + Passive Stereo Speakers
Power Supply 19v ASUS PowerBrick
Software openSUSE Tumbleweed
#13
What's is tRCDWA & tRCDRA? I know what the others are.

Time/Row/Column/Delay/?/?
this is what i found months ago searching online
https://docs.google.com/document/d/1CB8AtN0LhfR-kH0hi4pm6eMJfE3CNLLHB2bYt-nGpHI/edit
TRCDW =“Number of cycles from active to write”
TRCDWA = “ Number of cycles from active to write with auto-precharge. Same as TRCDW”
TRCDR = “Number of cycles from active to read”
TRCDRA = “Number of cycles from active to read with auto-precharge. Same as TRCDR”
 
Joined
May 12, 2017
Messages
341 (0.48/day)
Likes
137
#14
80-8192-160615
Memory Timings (Samsung) tRCDW-tRCDWA-tRCDR-tRCDRA
this is what i found months ago searching online
https://docs.google.com/document/d/1CB8AtN0LhfR-kH0hi4pm6eMJfE3CNLLHB2bYt-nGpHI/edit
TRCDW =“Number of cycles from active to write”
TRCDWA = “ Number of cycles from active to write with auto-precharge. Same as TRCDW”
TRCDR = “Number of cycles from active to read”
TRCDRA = “Number of cycles from active to read with auto-precharge. Same as TRCDR”
Thanks, but I need to know what the "A" stands for. I'll take a wild guess & say Array, but I will do some digging to see if I am correct.
 
Joined
Apr 5, 2015
Messages
17 (0.01/day)
Likes
7
System Name AMD ITX
Processor Athlon 5350@2.3GHz 1.3v
Motherboard AsRock AM1H-ITX
Cooling Artic Cooling AM1 Passive
Memory 8GB Samsung LP@1900MHz 1.65v
Storage 1TB WD Black 3.5" HDD + 750GB 2.5" HDD
Display(s) Lenovo 22" 16:10 1680x1050
Case Cooltek ITX Mini Cube
Audio Device(s) Scythe SDA-2100 + Passive Stereo Speakers
Power Supply 19v ASUS PowerBrick
Software openSUSE Tumbleweed
#15
Thanks, but I need to know what the "A" stands for. I'll take a wild guess & say Array, but I will do so digging to see if I am correct.
"with auto-precharge"
 
Joined
Mar 18, 2015
Messages
1,784 (1.19/day)
Likes
1,019
Location
Long Island
#17
I have seen some games do better with low latency and some do better with more speed.... so like many things, there's no 100% answer. One rule of thumb, anad again by no means a 100% predictor, is this:

CAS x 1000 / Latency....lowest number wins

CAS 15 x 1000 / DDR 3000 = 0.500 ms
CAS 16 x 1000 / DDR 3200 = 0.500 ms

To determine moire accurately.... have to test every pairing
 
Joined
May 12, 2017
Messages
341 (0.48/day)
Likes
137
#18
Looking at the timing posted in this thread needs proper investigation.

This is what's grabbing my eyes.

At the lower end (slowest speed) TRCDxx are almost on the same clock cycle, but at the highest speed their very far apart. WHY? This must be solved first,

In my testing on normal DDR, did you know that TRCD is partly responsible for micro-stutter. I have no idea if it applies to VRAM, but I will take a wild guess & say, yes it does.

The timing spread is going to have an effect on performance, that's 100% certain, that's why it is there, but it's only generic to cover all cards.

I have seen some games do better with low latency and some do better with more speed.... so like many things, there's no 100% answer. One rule of thumb, anad again by no means a 100% predictor, is this:

CAS x 1000 / Latency....lowest number wins

CAS 15 x 1000 / DDR 3000 = 0.500 ms
CAS 16 x 1000 / DDR 3200 = 0.500 ms

To determine moire accurately.... have to test every pairing
CAS on it's own does not determined the overall performance of DDRx. The link I posted in this thread does not take into account TRCD & TRP.

When all three timing are on the "same clock cycle" (important), it's going to have an effect on other timings which will also be lower (faster). This is where the lower latency DDRx pulls ahead.
 
Last edited:
Joined
Apr 5, 2015
Messages
17 (0.01/day)
Likes
7
System Name AMD ITX
Processor Athlon 5350@2.3GHz 1.3v
Motherboard AsRock AM1H-ITX
Cooling Artic Cooling AM1 Passive
Memory 8GB Samsung LP@1900MHz 1.65v
Storage 1TB WD Black 3.5" HDD + 750GB 2.5" HDD
Display(s) Lenovo 22" 16:10 1680x1050
Case Cooltek ITX Mini Cube
Audio Device(s) Scythe SDA-2100 + Passive Stereo Speakers
Power Supply 19v ASUS PowerBrick
Software openSUSE Tumbleweed
#19
Done some tests:
RX480 8GB > RX580 Bios
GPU 1300Mhz / Fan 100% / 150W+50%TDP / Performance Windows Profile / Win10 Airplane Mode

Test n.1
Memory 2100Mhz - 8400Mhz No EDC Errors
OCLMembench 244GB/s
Superposition Benchmark (3 Runs)
Custom Preset: Resolution=5K / Texture=High / Shader=Low / DOF=OFF
Min FPS = 23
Avg FPS = 28.7
Max FPS = 35.2
Score = 3834 (+/- 2)
####SEQ_WR_CTL_D1####
DAT_DLY = 7
DQS_DLY = 7
DQS_XTR = 0
DAT_2Y_DLY = 0
ADR_2Y_DLY = 0
CMD_2Y_DLY = 0
OEN_DLY = 7
OEN_EXT = 0
OEN_SEL = 0
ODT_DLY = 0
ODT_EXT = 0
ADR_DLY = 0
CMD_DLY = 0
####SEQ_WR_CTL_2####
DAT_DLY_H_D0 = 0
DQS_DLY_H_D0 = 0
OEN_DLY_H_D0 = 0
DAT_DLY_H_D1 = 0
DQS_DLY_H_D1 = 0
OEN_DLY_H_D1 = 0
WCDR_EN = 0
####SEQ_PMG_TIMING####
TCKSRE = 2
TCKSRX = 2
TCKE_PULSE = 12
TCKE = 12
SEQ_IDLE = 7
TCKE_PULSE_MSB = 0
SEQ_IDLE_SS = 0
####SEQ_RAS_TIMING####
TRCDW = 13
TRCDWA = 13
TRCDR = 24
TRCDRA = 24
TRRD = 5
TRC = 66
####SEQ_CAS_TIMING####
TNOPW = 0
TNOPR = 0
TR2W = 31
TCCDL = 4
TCCDS = 5
TW2R = 15
TCL = 21
####SEQ_MISC_TIMING####
TRP_WRA = 48
TRP_RDA = 26
TRP = 28
TRFC = 137
####SEQ_MISC_TIMING2####
PA2RDATA = 0
PA2WDATA = 0
TFAW = 0
TCRCRL = 3
TCRCWL = 7
T32AW = 0
TWDATATR = 0
####ARB_DRAM_TIMING####
ACTRD = 17
ACTWR = 17
RASMACTRD = 47
RASMACTWR = 63
####ARB_DRAM_TIMING2####
RAS2RAS = 187
RP = 53
WRPLUSRP = 64
BUS_TURN = 25
####MC_SEQ_MISC####
MC_SEQ_MISC1 = 0x2014030B
MC_SEQ_MISC3 = 0xA00089FA
MC_SEQ_MISC8 = 0x00000003


Test n.2
Memory 2150Mhz - 8600Mhz No EDC Errors
OCLMembench 234GB/s
Superposition Benchmark (3 Runs)
Custom Preset: Resolution=5K / Texture=High / Shader=Low / DOF=OFF
Min FPS = 23
Avg FPS = 28.7
Max FPS = 35.35
Score = 3846 (+/- 2)
####SEQ_WR_CTL_D1####
DAT_DLY = 7
DQS_DLY = 7
DQS_XTR = 0
DAT_2Y_DLY = 0
ADR_2Y_DLY = 0
CMD_2Y_DLY = 0
OEN_DLY = 7
OEN_EXT = 0
OEN_SEL = 0
ODT_DLY = 0
ODT_EXT = 0
ADR_DLY = 0
CMD_DLY = 0
####SEQ_WR_CTL_2####
DAT_DLY_H_D0 = 0
DQS_DLY_H_D0 = 0
OEN_DLY_H_D0 = 0
DAT_DLY_H_D1 = 0
DQS_DLY_H_D1 = 0
OEN_DLY_H_D1 = 0
WCDR_EN = 0
####SEQ_PMG_TIMING####
TCKSRE = 2
TCKSRX = 2
TCKE_PULSE = 12
TCKE = 12
SEQ_IDLE = 7
TCKE_PULSE_MSB = 0
SEQ_IDLE_SS = 0
####SEQ_RAS_TIMING####
TRCDW = 15
TRCDWA = 15
TRCDR = 25
TRCDRA = 25
TRRD = 5
TRC = 68
####SEQ_CAS_TIMING####
TNOPW = 0
TNOPR = 0
TR2W = 31
TCCDL = 4
TCCDS = 5
TW2R = 15
TCL = 21
####SEQ_MISC_TIMING####
TRP_WRA = 48
TRP_RDA = 26
TRP = 28
TRFC = 140
####SEQ_MISC_TIMING2####
PA2RDATA = 0
PA2WDATA = 0
TFAW = 0
TCRCRL = 3
TCRCWL = 7
T32AW = 0
TWDATATR = 0
####ARB_DRAM_TIMING####
ACTRD = 18
ACTWR = 18
RASMACTRD = 48
RASMACTWR = 63
####ARB_DRAM_TIMING2####
RAS2RAS = 170
RP = 53
WRPLUSRP = 64
BUS_TURN = 25
####MC_SEQ_MISC####
MC_SEQ_MISC1 = 0x20140514
MC_SEQ_MISC3 = 0xA00089FA
MC_SEQ_MISC8 = 0x00000003

Keep in mind that the v4/2150Mhz timings are not "super optimized", while the v3/2100Mhz timings are very(very) optimized for my card.
I'm probably not proving something here, but what i can notice is that with 8.6Ghz memory and a "ok/kinda decent set of timings" i can score the same or a little higher than a super tight set of timings with a slower clocked memory.
I used the Superposition benchmark because i find it very consistent, and at 5K with high texture/low shader i hope to push the ROPs/Memory very hard, using as much bandwith as possible.
i can't go higher than 2150Mhz/8.6Ghz because of the IMC...i see EDC errors @8.7Ghz
 
Joined
May 12, 2017
Messages
341 (0.48/day)
Likes
137
#20
Done some tests:
RX480 8GB > RX580 Bios
GPU 1300Mhz / Fan 100% / 150W+50%TDP / Performance Windows Profile / Win10 Airplane Mode

Test n.1
Memory 2100Mhz - 8400Mhz No EDC Errors
OCLMembench 244GB/s
Superposition Benchmark (3 Runs)
Custom Preset: Resolution=5K / Texture=High / Shader=Low / DOF=OFF
Min FPS = 23
Avg FPS = 28.7
Max FPS = 35.2
Score = 3834 (+/- 2)
####SEQ_WR_CTL_D1####
DAT_DLY = 7
DQS_DLY = 7
DQS_XTR = 0
DAT_2Y_DLY = 0
ADR_2Y_DLY = 0
CMD_2Y_DLY = 0
OEN_DLY = 7
OEN_EXT = 0
OEN_SEL = 0
ODT_DLY = 0
ODT_EXT = 0
ADR_DLY = 0
CMD_DLY = 0
####SEQ_WR_CTL_2####
DAT_DLY_H_D0 = 0
DQS_DLY_H_D0 = 0
OEN_DLY_H_D0 = 0
DAT_DLY_H_D1 = 0
DQS_DLY_H_D1 = 0
OEN_DLY_H_D1 = 0
WCDR_EN = 0
####SEQ_PMG_TIMING####
TCKSRE = 2
TCKSRX = 2
TCKE_PULSE = 12
TCKE = 12
SEQ_IDLE = 7
TCKE_PULSE_MSB = 0
SEQ_IDLE_SS = 0
####SEQ_RAS_TIMING####
TRCDW = 13
TRCDWA = 13
TRCDR = 24
TRCDRA = 24
TRRD = 5
TRC = 66
####SEQ_CAS_TIMING####
TNOPW = 0
TNOPR = 0
TR2W = 31
TCCDL = 4
TCCDS = 5
TW2R = 15
TCL = 21
####SEQ_MISC_TIMING####
TRP_WRA = 48
TRP_RDA = 26
TRP = 28
TRFC = 137
####SEQ_MISC_TIMING2####
PA2RDATA = 0
PA2WDATA = 0
TFAW = 0
TCRCRL = 3
TCRCWL = 7
T32AW = 0
TWDATATR = 0
####ARB_DRAM_TIMING####
ACTRD = 17
ACTWR = 17
RASMACTRD = 47
RASMACTWR = 63
####ARB_DRAM_TIMING2####
RAS2RAS = 187
RP = 53
WRPLUSRP = 64
BUS_TURN = 25
####MC_SEQ_MISC####
MC_SEQ_MISC1 = 0x2014030B
MC_SEQ_MISC3 = 0xA00089FA
MC_SEQ_MISC8 = 0x00000003


Test n.2
Memory 2150Mhz - 8600Mhz No EDC Errors
OCLMembench 234GB/s
Superposition Benchmark (3 Runs)
Custom Preset: Resolution=5K / Texture=High / Shader=Low / DOF=OFF
Min FPS = 23
Avg FPS = 28.7
Max FPS = 35.35
Score = 3846 (+/- 2)
####SEQ_WR_CTL_D1####
DAT_DLY = 7
DQS_DLY = 7
DQS_XTR = 0
DAT_2Y_DLY = 0
ADR_2Y_DLY = 0
CMD_2Y_DLY = 0
OEN_DLY = 7
OEN_EXT = 0
OEN_SEL = 0
ODT_DLY = 0
ODT_EXT = 0
ADR_DLY = 0
CMD_DLY = 0
####SEQ_WR_CTL_2####
DAT_DLY_H_D0 = 0
DQS_DLY_H_D0 = 0
OEN_DLY_H_D0 = 0
DAT_DLY_H_D1 = 0
DQS_DLY_H_D1 = 0
OEN_DLY_H_D1 = 0
WCDR_EN = 0
####SEQ_PMG_TIMING####
TCKSRE = 2
TCKSRX = 2
TCKE_PULSE = 12
TCKE = 12
SEQ_IDLE = 7
TCKE_PULSE_MSB = 0
SEQ_IDLE_SS = 0
####SEQ_RAS_TIMING####
TRCDW = 15
TRCDWA = 15
TRCDR = 25
TRCDRA = 25
TRRD = 5
TRC = 68
####SEQ_CAS_TIMING####
TNOPW = 0
TNOPR = 0
TR2W = 31
TCCDL = 4
TCCDS = 5
TW2R = 15
TCL = 21
####SEQ_MISC_TIMING####
TRP_WRA = 48
TRP_RDA = 26
TRP = 28
TRFC = 140
####SEQ_MISC_TIMING2####
PA2RDATA = 0
PA2WDATA = 0
TFAW = 0
TCRCRL = 3
TCRCWL = 7
T32AW = 0
TWDATATR = 0
####ARB_DRAM_TIMING####
ACTRD = 18
ACTWR = 18
RASMACTRD = 48
RASMACTWR = 63
####ARB_DRAM_TIMING2####
RAS2RAS = 170
RP = 53
WRPLUSRP = 64
BUS_TURN = 25
####MC_SEQ_MISC####
MC_SEQ_MISC1 = 0x20140514
MC_SEQ_MISC3 = 0xA00089FA
MC_SEQ_MISC8 = 0x00000003

Keep in mind that the v4/2150Mhz timings are not "super optimized", while the v3/2100Mhz timings are very(very) optimized for my card.
I'm probably not proving something here, but what i can notice is that with 8.6Ghz memory and a "ok/kinda decent set of timings" i can score the same or a little higher than a super tight set of timings with a slower clocked memory.
I used the Superposition benchmark because i find it very consistent, and at 5K with high texture/low shader i hope to push the ROPs/Memory very hard, using as much bandwith as possible.
i can't go higher than 2150Mhz/8.6Ghz because of the IMC...i see EDC errors @8.7Ghz
You have now posted extended list of memory timings. I just read again what the OP is saying. He stating he has higher performance with 3Dmark with lower VRAM clock speed. If this is the case, then it clearly shows lower latency VRAM timings is the way to go.
 
Joined
Mar 10, 2010
Messages
6,227 (1.87/day)
Likes
2,382
Location
Manchester uk
System Name RyzenGtEvo
Processor Amd R5 2600X@4.1
Motherboard Crosshair hero7 @bios 1201
Cooling 360EK extreme rad+ 360$EK slim all push, cpu Monoblock Gpu full cover all EK
Memory Gigabyte Aurus Rgb 16Gb in two sticks.
Video Card(s) Sapphire refference Rx vega 64 waterblockedEK
Storage Samsung Nvme Pg981 samsung 840, WD 1Tb+2Tb +3Tbgrn, 1tb seagate sshd hybrid(games)
Display(s) Samsung uea28"850R 4k freesync, LG 49" 4K 60hz ,Oculus
Case Lianli p0-11 dynamic
Audio Device(s) Xfi creative 7.1 on board ,Yamaha dts av setup, corsair void pro
Power Supply corsair 1200Hxi
Mouse Roccat Kova
Keyboard Roccat Iksu force fx
Software Win 10 Pro
Benchmark Scores 8056 vega 3dmark timespy
#21
Forgot to mention my Rx 580 is the 4GB version so default ram frequency is only 1750.
Kastriot: Why do you think 2000MHz is faster than 2150MHz, do you mean I should find the lowest memory strap that's stable @2GHz?
Amd graphics cards incorporated a version of error check and control and at the highest just stable end you loose performance because of repeated memory requests so sometimes faster is slower.
But different game's definitely also favour one ir the other sometimes ,most games love lower latency though IMHO.
I had 480s with custom straps for mining that gamed really well with 268.5Gb/s bandwidth.
In the end you can increase that figure either way or both but that's what matters.
 
Joined
Apr 5, 2015
Messages
17 (0.01/day)
Likes
7
System Name AMD ITX
Processor Athlon 5350@2.3GHz 1.3v
Motherboard AsRock AM1H-ITX
Cooling Artic Cooling AM1 Passive
Memory 8GB Samsung LP@1900MHz 1.65v
Storage 1TB WD Black 3.5" HDD + 750GB 2.5" HDD
Display(s) Lenovo 22" 16:10 1680x1050
Case Cooltek ITX Mini Cube
Audio Device(s) Scythe SDA-2100 + Passive Stereo Speakers
Power Supply 19v ASUS PowerBrick
Software openSUSE Tumbleweed
#22
You have now posted extended list of memory timings. I just read again what the OP is saying. He stating he has higher performance with 3Dmark with lower VRAM clock speed. If this is the case, then it clearly shows lower latency VRAM timings is the way to go.
We still don't know if his 2400mhz memory clock is "stable" and if there are EDC errors. We don't know anything about the specific memory brand he is using, timings, we also have no 3dmark scores from him ... i really still can't see any "proof of concept" here.
I'm really curious to do more test and gather more data about this subject, we can't decide on personal opinions.
Any idea on how i can do some more in-depth tests?

Amd graphics cards incorporated a version of error check and control and at the highest just stable end you loose performance because of repeated memory requests so sometimes faster is slower.
But different game's definitely also favour one ir the other sometimes ,most games love lower latency though IMHO.
I had 480s with custom straps for mining that gamed really well with 268.5Gb/s bandwidth.
In the end you can increase that figure either way or both but that's what matters.
are we talking about latency in nanoseconds or in clock cycles?
 
Joined
Mar 10, 2010
Messages
6,227 (1.87/day)
Likes
2,382
Location
Manchester uk
System Name RyzenGtEvo
Processor Amd R5 2600X@4.1
Motherboard Crosshair hero7 @bios 1201
Cooling 360EK extreme rad+ 360$EK slim all push, cpu Monoblock Gpu full cover all EK
Memory Gigabyte Aurus Rgb 16Gb in two sticks.
Video Card(s) Sapphire refference Rx vega 64 waterblockedEK
Storage Samsung Nvme Pg981 samsung 840, WD 1Tb+2Tb +3Tbgrn, 1tb seagate sshd hybrid(games)
Display(s) Samsung uea28"850R 4k freesync, LG 49" 4K 60hz ,Oculus
Case Lianli p0-11 dynamic
Audio Device(s) Xfi creative 7.1 on board ,Yamaha dts av setup, corsair void pro
Power Supply corsair 1200Hxi
Mouse Roccat Kova
Keyboard Roccat Iksu force fx
Software Win 10 Pro
Benchmark Scores 8056 vega 3dmark timespy
#23
We still don't know if his 2400mhz memory clock is "stable" and if there are EDC errors. We don't know anything about the specific memory brand he is using, timings, we also have no 3dmark scores from him ... i really still can't see any "proof of concept" here.
I'm really curious to do more test and gather more data about this subject, we can't decide on personal opinions.
Any idea on how i can do some more in-depth tests?


are we talking about latency in nanoseconds or in clock cycles?
both equate to the same thing nanoseconds ,saved.
 
Top