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

Intel "Ice Lake" GPU Docs Reveal Unganged Memory Mode

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
36,667 (8.70/day)
Likes
18,909
Location
Hyderabad, India
Processor AMD Ryzen 7 2700X
Motherboard MSI B450 Gaming Pro Carbon AC
Cooling AMD Wraith Prism
Memory 2x 16GB Corsair Vengeance LPX DDR4-3000
Video Card(s) Colorful iGame GTX 1070 Ti Vulcan X
Storage Western Digital Black NVMe 512GB
Display(s) Samsung U28D590 28-inch 4K UHD
Case Corsair Carbide 100R
Audio Device(s) Creative Sound Blaster Recon3D PCIe
Power Supply Antec EarthWatts Pro Gold 750W
Mouse Razer Abyssus
Keyboard Microsoft Sidewinder X4
Software Windows 10 Pro
#1
When reading through the Gen11 GT2 whitepaper by Intel, which describes their upcoming integrated graphics architecture, we may have found a groundbreaking piece of information that concerns the memory architecture of computers running 10 nm "Ice Lake" processors. The whitepaper mentions the chip to feature a 4x32-bit LPDDR4/DDR4 interface as opposed to the 2x64-bit LPDDR4/DDR4 interface of current-generation chips such as "Coffee Lake." This is strong evidence that Intel's new architecture will have unganged dual-channel memory controllers (2x 64-bit), as opposed to the monolithic 128-bit IMC found on current-generation chips.

An unganged dual-channel memory interface consists of two independent memory controllers, each handling a 64-bit wide memory channel. This approach lets the processor execute two operations in tandem, given the accesses go to distinct memory banks. On top of that it's now possible to read and write at the same time, something that's can't be done in 128-bit memory mode. From a processor's perspective DRAM is very slow, and what takes up most of the time (= latency), is opening the memory and preparing the read/write operation - the actual data transfer is fairly quick.



With two independent memory controllers these latencies can be mitigated, in several ways in unganged mode. While single-threaded workloads, or workloads that operate on a relatively small problem set, benefit more from ganged mode, unganged mode can shine when multiple (or multi-threaded) applications work with vast amounts of memory, which increases the likelihood that two independent banks of memory get accessed. Perhaps unganged-aware software, such as OS-level memory management could help make the most out of unganged mode, by trying to spread out processes evenly throughout the physical memory, so independent memory accesses can be executed as often as possible.

For integrated graphics, unganged mode is a real killer application though. The iGPU reserves a chunk of system memory for geometry, textures and framebuffer. This memory range is typically placed at the end of the physical memory space, whereas the Windows OS and applications usually are located near the start of physical memory. This effectively gives the GPU its own dedicated memory controller, which also reduces memory latency, because one controller can hold the IGP's memory pages open almost all the time, whereas the second controller takes care of the OS and application memory requests.

AMD has been supporting unganged dual-channel memory interfaces for over a decade now. The company's first Phenom processors introduced unganged memory with a BIOS option to force the CPU to interleave all data, called ganged mode. The consensus among the tech-community over the past ten years and the evolution of the modern processor toward more parallelism favors unganged mode. With CPU core counts heading north of 8 for mainstream-desktop processors, and integrated GPUs becoming the norm, it was natural for Intel to add support for an unganged memory interface.

Image Courtesy: ilsistemista.net

View at TechPowerUp Main Site
 
Joined
Jan 11, 2005
Messages
1,187 (0.23/day)
Likes
435
Location
66 feet from the ground
System Name 2nd AMD puppy
Processor FX-8350 vishera
Motherboard Gigabyte GA-970A-UD3
Cooling Cooler Master Hyper TX2
Memory 16 Gb DDR3:8GB Kingston HyperX Beast + 8Gb G.Skill Sniper(by courtesy of tabascosauz &TPU)
Video Card(s) Sapphire RX 580 Nitro+;1450/2000 Mhz
Storage SSD :840 pro 128 Gb;Iridium pro 240Gb ; HDD 2xWD-1Tb
Display(s) Benq XL2730Z 144 Hz freesync
Case NZXT 820 PHANTOM
Audio Device(s) Audigy SE with Logitech Z-5500
Power Supply Cooleer Master RP M520
Mouse Razer copperhead / Gamdias zeus (by courtesy of sneekypeet & TPU)
Keyboard MS Sidewinder x4
Software win10 64bit ltsc
Benchmark Scores irrelevant for me
#2
so amd approach was better and they do the same..

seems they try to improve the perf. this way also; if i read between lines .... they're aware of having perf. issues vs amd.... "Houston, we have a problem"
 
Joined
Oct 26, 2008
Messages
2,092 (0.55/day)
Likes
401
System Name Budget AMD System
Processor Threadripper 1900X @ 4.025Ghz (100x40.25 @ 1.325V)
Motherboard Gigabyte X399 Aorus Gaming 7
Cooling EKWB X399 Monoblock
Memory 4x8GB GSkill TridentZ RGB 14-14-14-34 CR1 @ 2933
Video Card(s) XFX Radeon RX Vega₆⁴ Liquid @ 1,800Mhz Core, 1100 HBM2
Storage 1x ADATA SX8200 NVMe, 1x Segate 2.5" FireCuda 2TB SATA, 1x 500GB HGST SATA
Display(s) Vizio 22" 1080p 60hz TV (Samsung Panel)
Case Corsair 570X
Audio Device(s) Onboard
Power Supply Seasonic X Series 850W KM3
Software Windows 10 Pro x64
#3
Intel got complacent. Now they are paying for it. MASSIVELY.
 
Joined
Nov 4, 2005
Messages
10,243 (2.08/day)
Likes
2,657
System Name MoFo 2
Processor AMD PhenomII 1100T @ 4.2Ghz
Motherboard Asus Crosshair IV
Cooling Swiftec 655 pump, Apogee GT,, MCR360mm Rad, 1/2 loop.
Memory 8GB DDR3-2133 @ 1900 8.9.9.24 1T
Video Card(s) HD7970 1250/1750
Storage Agility 3 SSD 6TB RAID 0 on RAID Card
Display(s) 46" 1080P Toshiba LCD
Case Rosewill R6A34-BK modded (thanks to MKmods)
Audio Device(s) ATI HDMI
Power Supply 750W PC Power & Cooling modded (thanks to MKmods)
Software A lot.
Benchmark Scores Its fast. Enough.
#5
If the IGP is really worth a damn they found the same issue AMD faces, how to feed the high efficiency parallel shader cores fast enough to make them work while not starving your CPU cores.
 
Likes: R-T-B
Joined
Feb 19, 2009
Messages
895 (0.24/day)
Likes
230
Location
I live in Norway, in the province Buskerud.
System Name 2 sys spec seperated by "|"
Processor R7 1700 @ 3.9| Xeon 2680v2
Motherboard Asrock B350M Pro 4 | HP Z620
Cooling Water1x360,1x240 | Air
Memory 64gb G.skill SniperX 3200mhz CL16 | 128 gb
Video Card(s) EK-FC - RX Vega 64 | GTX970
Storage 960 Evo 500gb, 860 evo 1tb, Intel 660P 1tb PM871 256gb | various intel ssd's.
Display(s) AOC 28" 4K something + 1440p 144hz something.
Case Phanteks EvolvX M-Atx
Power Supply Corsair RM850
Mouse G402
Keyboard TT Meka G1
#6
so amd approach was better and they do the same..

seems they try to improve the perf. this way also; if i read between lines .... they're aware of having perf. issues vs amd.... "Houston, we have a problem"
it may explain how vega is doing so well in the apu's.
 
Joined
Mar 22, 2011
Messages
146 (0.05/day)
Likes
51
Location
USA
System Name Rump Shaker '19
Processor 8700K, Delided w/Rocket Copper IHS on Bitspower monoblock
Motherboard Gigabyte Z370X Gaming-7
Cooling BP and Watercool custom loop NB eLoop fans covering 6x120mm radiator area with14mm PETG hard tubing
Memory 16GB (2x8GB) DDR4@3200 C14-14-14
Video Card(s) EVGA GeForce RTX 2080ti on Bykski waterblock
Storage Samsung 970 PRO 512GB, Samsung 960 EVO 500GB, (2)Samsung 850 EVO 500GB, 1TB MX500, (2)WD Red 8TB
Display(s) Dell S2716DG 27" 1440p G-SYNC, Samsung Odyssey
Case Phanteks Evolv X
Audio Device(s) Creative Sound BlasterX AE-5, Logitech Z906 5.1 speaker system
Power Supply Cooler Master V1200, custom sleeved white cables
Mouse Logitech G500s
Keyboard Corsair K70 Lux RGB
Software Wi10 Pro 64-bit
#7
Joined
Sep 17, 2014
Messages
8,497 (5.06/day)
Likes
7,543
Location
Duiven, Netherlands
Processor i7 8700k 4.7Ghz @ 1.26v
Motherboard AsRock Fatal1ty K6 Z370
Cooling beQuiet! Dark Rock Pro 3
Memory 16GB Corsair Vengeance LPX 3200/C16
Video Card(s) MSI GTX 1080 Gaming X @ 2100/5500
Storage Samsung 850 EVO 1TB + Samsung 830 256GB + Crucial BX100 250GB + Toshiba 1TB HDD
Display(s) Eizo Foris FG2421
Case Fractal Design Define C TG
Power Supply EVGA G2 750w
Mouse Logitech G502 Protheus Spectrum
Keyboard Sharkoon MK80 (Brown)
Software W10 x64
#8
Come on, we all know Intel is straight up copy/pasting technology to quickly get in the higher end of GPUs. This can not be a surprise. Great minds think alike; or look in each others' garden.
 
Joined
Aug 13, 2010
Messages
4,252 (1.34/day)
Likes
2,511
#9
Come on, we all know Intel is straight up copy/pasting technology to quickly get in the higher end of GPUs. This can not be a surprise. Great minds think alike; or look in each others' garden.
They might even try trickier stuff in the future. I don't trust this Raja dude and the Keller whats-his-face. They look like they might copy other people's design like Vega or Ryzen or something. Don't trust those, they look snakey
 
Joined
Mar 10, 2015
Messages
1,438 (0.96/day)
Likes
954
System Name Wut?
Processor 4770K @ Stock
Motherboard MSI Z97 Gaming 7
Cooling Water
Memory 16GB DDR3 2400
Video Card(s) Vega 56
Storage Samsung 840 Pro 256GB
Display(s) 3440 x 1440
Case Thermaltake T81
Power Supply Seasonic 750 Watt Gold
#10
They might even try trickier stuff in the future. I don't trust this Raja dude and the Keller whats-his-face. They look like they might copy other people's design like Vega or Ryzen or something. Don't trust those, they look snakey
I would hope they would copy someone else's GPU.
 

eidairaman1

The Exiled Airman
Joined
Jul 2, 2007
Messages
25,857 (6.00/day)
Likes
8,893
Location
Republic of Texas (True Patriot)
System Name PCGOD
Processor AMD FX 8350@ 5.0GHz
Motherboard Asus TUF 990FX Sabertooth R2 2901 Bios
Cooling Scythe Ashura, 2×BitFenix 230mm Spectre Pro LED (Blue,Green), 2x BitFenix 140mm Spectre Pro LED
Memory 16 GB Gskill Ripjaws X 2133 (2400 OC, 10-10-12-20-20, 1T, 1.65V)
Video Card(s) AMD Radeon 290 Sapphire Vapor-X
Storage Samsung 840 Pro 256GB, WD Velociraptor 1TB
Display(s) NEC Multisync LCD 1700V (Display Port Adapter)
Case AeroCool Xpredator Evil Blue Edition
Audio Device(s) Creative Labs Sound Blaster ZxR
Power Supply Seasonic 1250 XM2 Series (XP3)
Mouse Roccat Kone XTD
Keyboard Roccat Ryos MK Pro
Software Windows 7 Pro 64
#12
They're really not though:



AMD for reference:

Considering AMD has had ganged and unganged mode along with ECC definitely on AM3 and I believe even since AM2, yes Intel has been very complacent.
 
Joined
Sep 27, 2014
Messages
409 (0.25/day)
Likes
199
#13
Cache memory solves that problem. Level one at CPU core, level two at cluster level...
Only cache misses have to be read from or written to memory.
I don't see as being a huge performance factor.
 
Joined
Jan 8, 2017
Messages
3,987 (4.78/day)
Likes
3,103
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
#14
Cache memory solves that problem. Level one at CPU core, level two at cluster level...
Only cache misses have to be read from or written to memory.
I don't see as being a huge performance factor.
Caches are unfortunately not very useful for GPU architectures, they need a lot of instructions/data delivered all at once as opposed to a few instructions/data delivered very quickly as is the case with a CPU (that's a very primitive description but it's good enough).

They need a lot of bandwidth which is rather scarce on the current DDR4 platform, AMD faces the same problem.
 
Joined
Oct 22, 2014
Messages
6,958 (4.23/day)
Likes
4,134
Location
Sunshine Coast
System Name Black Box
Processor Intel Xeon E5-2680 10c/20t 2.8GHz @ 3.0GHz
Motherboard Asrock X79 Extreme 11
Cooling Coolermaster 240 RGB A.I.O.
Memory G. Skill 16Gb (4x4Gb) 2133Mhz
Video Card(s) Nvidia GTX 710
Storage Sandisk X 400 256Gb
Display(s) AOC 22" Freesync 1m.s. 75Hz
Case Corsair 450D High Air Flow.
Audio Device(s) No need.
Power Supply FSP Aurum 650W
Mouse Yes
Keyboard Of course
Software W10 Home Premium 64 bit
#15
Come on, we all know Intel is straight up copy/pasting technology to quickly get in the higher end of GPUs. This can not be a surprise. Great minds think alike; or look in each others' garden.
Reverse engineering is common, yet when the Chinese do it people crack a sad and spit the dummy over lost jobs and revenues.
 
Joined
Oct 27, 2009
Messages
651 (0.19/day)
Likes
253
Location
Republic of Texas
System Name [H]arbringer
Processor 4x 61XX ES @3.5Ghz (48cores)
Motherboard SM GL
Cooling 3x xspc rx360, rx240, 4x DT G34 snipers, D5 pump.
Memory 16x gskill DDR3 1600 cas6 2gb
Video Card(s) blah bigadv folder no gfx needed
Storage 32GB Sammy SSD
Display(s) headless
Case Xigmatek Elysium (whats left of it)
Audio Device(s) yawn
Power Supply Antec 1200w HCP
Software Ubuntu 10.10
Benchmark Scores http://valid.canardpc.com/show_oc.php?id=1780855 http://www.hwbot.org/submission/2158678 http://ww
#16
Reverse engineering is common, yet when the Chinese do it people crack a sad and spit the dummy over lost jobs and revenues.
Going to assume you are joking, One is innovation, the other is espionage.
Anyone can steal someones entire IP and manufacture the design.
To figure out how it works, iterate on the design and compete... that is innovation.

Caches are unfortunately not very useful for GPU architectures, they need a lot of instructions/data delivered all at once as opposed to a few instructions/data delivered very quickly as is the case with a CPU (that's a very primitive description but it's good enough).

They need a lot of bandwidth which is rather scarce on the current DDR4 platform, AMD faces the same problem.
Yeah, the 2200g can keep pace with the 2400g when clocked the same despite the ~40% increase in sp, definitely memory starved.
 
Last edited:
Top