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

Intel Xe HPG Graphics Architecture and Arc "Alchemist" GPU Detailed

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
46,278 (7.69/day)
Location
Hyderabad, India
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard ASUS ROG Strix B450-E Gaming
Cooling DeepCool Gammax L240 V2
Memory 2x 8GB G.Skill Sniper X
Video Card(s) Palit GeForce RTX 2080 SUPER GameRock
Storage Western Digital Black NVMe 512GB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) ASUS SupremeFX S1220A
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Gamdias Hermes E2
Software Windows 11 Pro
It's happening, Intel is taking a very pointy stab at the AAA gaming graphics market, taking the fight to NVIDIA GeForce and AMD Radeon. The Arc "Alchemist" discrete GPU implements the Xe HPG (high performance gaming) graphics architecture, and offers full DirectX 12 Ultimate compatibility. It also offers contemporary features gamers want, such as XeSS, an AI-supersampling feature rivaling DLSS and FSR. There's a lot more to the Xe HPG architecture than being a simple a scale-up from the Xe LP-based iGPUs found in today's "Tiger Lake" processors.

Just like Compute Units on AMD GPUs, and Streaming Multiprocessors on NVIDIA, Intel designed a scalable hierarchical compute hardware structure for Xe HPG. It begins with the Xe-core, an indivisible compute building block that contains 16 each of 256-bit vector engines and 1024-bit matrix engines. combined with basic load/store hardware and an L1 cache. The vector unit here is interchangeable with the execution unit, and the Xe-core contains 16 of these. The Render Slice is a collective of four Xe-cores, four Raytracing Units; and other common fixed-function hardware that include the geometry pipeline, rasterization pipeline, samplers, and pixel-backends. The Raytracing Units contain fixed-function hardware for bounding-box intersection, ray traversal, and triangle intersection.



Moving a level up from the Render Slice, we see a Global Dispatch processor, and the GPU's memory fabric, which begins with an L2 cache. This is where Intel can scale up its GPUs. The 6 nm "Alchemist" silicon features eight Render Slices sharing the memory subsystem and Global Dispatch. Intel can carve out variants by toggling entire Render Slices, or perhaps even individual Xe-cores. With 16 EUs per Xe-core, 4 Xe-cores per Render Slice, and 8 Render Slices, we arrive at 512 execution units, or 4,096 programmable shaders.



Given that Xe HPG is being designed for the TSMC N6 (6 nm) silicon fabrication node, Intel claims a 50% performance/Watt gain over Xe LP solutions built on Intel's own 10 nm SuperFin nodes, such as the DG1 Iris Xe MAX. As a performance discrete GPU, "Alchemist" enjoys a much larger power budget, and hence operates at much higher frequencies for the available hardware.



Although not mentioned in the Intel presentation, it's been extensively reported that "Alchemist" (or DG2) features a 256-bit wide GDDR6 memory interface. The company is yet to determine memory size, but given the memory speeds available in the market (14 Gbps, 16 Gbps, and 18 Gbps), the memory bandwidth can end up anywhere between 448 GB/s to 576 GB/s.

Armed with as many as 512x 1024-bit Matrix cores backed by Xe Matrix extensions "Alchemist" is expected to be an AI processing powerhouse, with Intel leveraging them both for the XeSS performance enhancement feature, as well as other real-time rendering applications, such as de-noising for the raytracing pipeline.


Intel Arc "Alchemist" is expected to see a market release in Q1 2022. The company is ready with a roadmap with at least three of its successors, the Xe2 "Battlemage," Xe3 "Celestial," and XeNext "Druid." With no time-scale mentioned in the slide, we don't know if Intel is executing one architecture every year.

View at TechPowerUp Main Site
 
Joined
Apr 15, 2021
Messages
844 (0.78/day)
I must be missing something. What all rendering engines would be able to take advantage of these cards? I know Iray is already off the table since that is specifically for NVidia branded cards.
 
Joined
Jun 18, 2021
Messages
2,251 (2.22/day)
out of topic but can you guys maybe do a summary of what's relevant from the recent Intel presentations? so many articles and so many parallel discussions, it's a bit hard to keep up
 
Joined
Jun 16, 2019
Messages
351 (0.20/day)
System Name Cyberdyne Systems Core
Processor AMD Sceptre 9 3950x Quantum neural processor (384 nodes)
Motherboard Cyberdyne X1470
Cooling Cyberdyne Superconduct SC5600
Memory 128TB QRAM
Storage SK 16EB NVMe PCI-E 9.0 x8
Display(s) Multiple LG C9 3D Matrix OLED Cube
Software Skysoft Skynet
I must be missing something. What all rendering engines would be able to take advantage of these cards? I know Iray is already off the table since that is specifically for NVidia branded cards.
Anything that can use directx/open gl/vulkan I would assume.
 
Joined
Jan 25, 2011
Messages
531 (0.11/day)
Location
Inside a mini ITX
System Name ITX Desktop
Processor Core i7 9700K
Motherboard Gigabyte Aorus Pro WiFi Z390
Cooling Arctic esports 34 duo.
Memory Corsair Vengeance LPX 16GB 3000MHz
Video Card(s) Gigabyte GeForce RTX 2070 Gaming OC White PRO
Storage Samsung 970 EVO Plus | Intel SSD 660p
Case NZXT H200
Power Supply Corsair CX Series 750 Watt
Looking at the raw specs, an 8 slice design can theoretically perform rasterization close to an RTX 3070 / Radeon 6800. Hopefully, the drivers will be good enough.
 
Joined
Apr 29, 2020
Messages
135 (0.09/day)
Given that Xe HPG is being designed for the TSMC N6 (6 nm) silicon fabrication node, Intel claims a 50% performance/Watt gain over Xe LP solutions built on Intel's own 10 nm SuperFin nodes, such as the DG1 Iris Xe MAX.
But I thought Intel 10nm was the same as TSMC 7nm, and TSMC certainly isn't claiming the 6nm optical shrink gains anything like 50% performance/watt uplift. Have Intel and various fanboys been lying all this time?
 
Joined
Aug 20, 2007
Messages
20,710 (3.41/day)
System Name Pioneer
Processor Ryzen R9 7950X
Motherboard GIGABYTE Aorus Elite X670 AX
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory 64GB (4x 16GB) G.Skill Flare X5 @ DDR5-6000 CL30
Video Card(s) XFX RX 7900 XTX Speedster Merc 310
Storage 2x Crucial P5 Plus 2TB PCIe 4.0 NVMe SSDs
Display(s) 55" LG 55" B9 OLED 4K Display
Case Thermaltake Core X31
Audio Device(s) TOSLINK->Schiit Modi MB->Asgard 2 DAC Amp->AKG Pro K712 Headphones or HDMI->B9 OLED
Power Supply FSP Hydro Ti Pro 850W
Mouse Logitech G305 Lightspeed Wireless
Keyboard WASD Code v3 with Cherry Green keyswitches
Software Windows 11 Enterprise (legit), Gentoo Linux x64
But I thought Intel 10nm was the same as TSMC 7nm, and TSMC certainly isn't claiming the 6nm optical shrink gains anything like 50% performance/watt uplift. Have Intel and various fanboys been lying all this time?
Yes and no.

You are discovering, unsurprisingly, that node names are incredibly misleading.

It is universal, sadly.
 
Joined
May 13, 2013
Messages
76 (0.02/day)
Location
MADAGASCAR, Antananarivo
System Name Righolder
Processor intel i5-4590
Motherboard Crap Mobo
Memory Gskill Trident-X 2133mhz 9-11-10-28-1N @1333
Video Card(s) r9 fury nitro 1020/500
Display(s) Philips 227ELH
Case Deepcool Dukase
Power Supply Raidmax RX-1200AE
Software Win 10 64bit
Shading Units: 4096
TMUs: 256
ROPs: 128
Compute units/SM Count/ Xe Cores: 32
RT Cores: 32
L1 Cache: ? KB
L2 Cache: ? MB
Memory Size: ? GB
Memory Type: GDDR6/X ?
Memory Bus: 256 bit ?
Bandwidth: 448 ~ 576 GB/s
-Spec wise, it's slightly less than a rx 6800 xt at 4608 vs 4096 shader (or 288 vs 256 TMUs)
-It will all depend on the gpu clocks the TSMC N6 will achieve, Intel is claiming 1.5x more than the Xe LP discrete; but we don't know 1.5x 1.1Ghz or 1.5Ghz...
-As for raytracing, it only has 32 RT cores, significantly less compared to 82 on Ampere and 80 on RDNA 2.0 but we don't know the performance of its RT core yet.
 
Joined
Feb 11, 2009
Messages
5,389 (0.98/day)
System Name Cyberline
Processor Intel Core i7 2600k -> 12600k
Motherboard Asus P8P67 LE Rev 3.0 -> Gigabyte Z690 Auros Elite DDR4
Cooling Tuniq Tower 120 -> Custom Watercoolingloop
Memory Corsair (4x2) 8gb 1600mhz -> Crucial (8x2) 16gb 3600mhz
Video Card(s) AMD RX480 -> ... nope still the same :'(
Storage Samsung 750 Evo 250gb SSD + WD 1tb x 2 + WD 2tb -> 2tb MVMe SSD
Display(s) Philips 32inch LPF5605H (television) -> Dell S3220DGF
Case antec 600 -> Thermaltake Tenor HTCP case
Audio Device(s) Focusrite 2i4 (USB)
Power Supply Seasonic 620watt 80+ Platinum
Mouse Elecom EX-G
Keyboard Rapoo V700
Software Windows 10 Pro 64bit
Yes and no.

You are discovering, unsurprisingly, that node names are incredibly misleading.

It is universal, sadly.

In this case its not so much about node names as it is about claims made, as they said it was Intel themselves who claimed the transistor count of their 10nm is on par with TSMC 7nm hence the whole renaming scheme of "Intel 7"
But now its claimed to have a 50% uplift going for TSMC 6nm which....well TSMC never claimed would be the improvement from such a relatively minor shrink.
 
Joined
Aug 20, 2007
Messages
20,710 (3.41/day)
System Name Pioneer
Processor Ryzen R9 7950X
Motherboard GIGABYTE Aorus Elite X670 AX
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory 64GB (4x 16GB) G.Skill Flare X5 @ DDR5-6000 CL30
Video Card(s) XFX RX 7900 XTX Speedster Merc 310
Storage 2x Crucial P5 Plus 2TB PCIe 4.0 NVMe SSDs
Display(s) 55" LG 55" B9 OLED 4K Display
Case Thermaltake Core X31
Audio Device(s) TOSLINK->Schiit Modi MB->Asgard 2 DAC Amp->AKG Pro K712 Headphones or HDMI->B9 OLED
Power Supply FSP Hydro Ti Pro 850W
Mouse Logitech G305 Lightspeed Wireless
Keyboard WASD Code v3 with Cherry Green keyswitches
Software Windows 11 Enterprise (legit), Gentoo Linux x64
Performance per watt has a lot to do with core design too. But it's all a bunch of marketing regardless until the chip is out.
 
Joined
Feb 13, 2016
Messages
3,061 (1.03/day)
Location
Buenos Aires
System Name Ryzen Monster
Processor Ryzen 5 5600X
Motherboard Asus ROG Crosshair Hero VII WiFi
Cooling Corsair H100i RGB Platinum
Memory Corsair Vengeance RGB Pro 32GB (4x8GB) 3200Mhz CMW16GX4M2C3200C16
Video Card(s) Asus ROG Strix RX5700XT OC 8Gb
Storage WD Black 500GB NVMe 250Gb Samsung SSD, OCZ 500Gb SSD WD M.2 500Gb, plus three spinners up to 1.5Tb
Display(s) LG 32GK650F-B 32" UltraGear™ QHD
Case Cooler Master Storm Trooper
Audio Device(s) Supreme FX on board
Power Supply Corsair RM850X full modular
Mouse Corsair M65 Pro
Keyboard Corsair Strafe RGB Silent
VR HMD Headphones Logitech G533 wireless
Software Windows 11 Start 11
Benchmark Scores 3DMark Time Spy 4532 (9258 March 2021, 9399 July 2021)
Will Intel allow board partners such as Asus, Sapphire etc to use their GPU chips? (Aka AIBs, I believe)
 
Last edited:
Joined
Mar 14, 2014
Messages
1,274 (0.35/day)
Processor i7-4790K 4.6GHz @1.29v
Motherboard ASUS Maximus Hero VII Z97
Cooling Noctua NH-U14S
Memory G. Skill Trident X 2x8GB 2133MHz
Video Card(s) Asus Tuf RTX 3060 V1 FHR (Newegg Shuffle)
Storage OS 120GB Kingston V300, Samsung 850 Pro 512GB , 3TB Hitachi HDD, 2x5TB Toshiba X300, 500GB M.2 @ x2
Display(s) Lenovo y27g 1080p 144Hz
Case Fractal Design Define R4
Audio Device(s) AKG Q701's w/ O2+ODAC (Sounds a little bright)
Power Supply EVGA Supernova G2 850w
Mouse Glorious Model D
Keyboard Rosewill Full Size. Red Switches. Blue Leds. RK-9100xBRE - Hate this. way to big
Software Win10
Benchmark Scores 3DMark FireStrike Score : needs updating
Wonder if they'll do anything like AMD did with their old APUs and 7770/7750 gpus.
 
Joined
Jan 14, 2019
Messages
9,725 (5.12/day)
Location
Midlands, UK
System Name Nebulon-B Mk. 4
Processor AMD Ryzen 7 7800X3D
Motherboard MSi PRO B650M-A WiFi
Cooling be quiet! Dark Rock 4
Memory 2x 24 GB Corsair Vengeance EXPO DDR5-6000
Video Card(s) Sapphire Pulse Radeon RX 7800 XT
Storage 2 TB Corsair MP600 GS, 2 TB Corsair MP600 R2, 4 + 8 TB Seagate Barracuda 3.5"
Display(s) Dell S3422DWG, 7" Waveshare touchscreen
Case Kolink Citadel Mesh black
Power Supply Seasonic Prime GX-750
Mouse Logitech MX Master 2S
Keyboard Logitech G413 SE
Software Windows 10 Pro
Benchmark Scores Cinebench R23 single-core: 1,800, multi-core: 18,000. Superposition 1080p Extreme: 9,900.
Such a clean architecture by the looks of it. Everything is some power of 2. The OCD in me likes it. Whether it will be any good in real life, we'll see.
 
Joined
Sep 17, 2014
Messages
20,780 (5.97/day)
Location
The Washing Machine
Processor i7 8700k 4.6Ghz @ 1.24V
Motherboard AsRock Fatal1ty K6 Z370
Cooling beQuiet! Dark Rock Pro 3
Memory 16GB Corsair Vengeance LPX 3200/C16
Video Card(s) ASRock RX7900XT Phantom Gaming
Storage Samsung 850 EVO 1TB + Samsung 830 256GB + Crucial BX100 250GB + Toshiba 1TB HDD
Display(s) Gigabyte G34QWC (3440x1440)
Case Fractal Design Define R5
Audio Device(s) Harman Kardon AVR137 + 2.1
Power Supply EVGA Supernova G2 750W
Mouse XTRFY M42
Keyboard Lenovo Thinkpad Trackpoint II
Software W10 x64
Looking at the raw specs, an 8 slice design can theoretically perform rasterization close to an RTX 3070 / Radeon 6800. Hopefully, the drivers will be good enough.

To be fair, that would be a fine performance level for Intel's debut. Enough for everyone, not hitting the top just yet.

But the real questions are:
- price
- form factors
- noise/heat/TDP
- feature set
 
Joined
May 20, 2020
Messages
1,283 (0.91/day)
I hope their "HiZ" unit is good at hidden surface removal at or near NVIDIA level with their Gigapixel derived tech; if so the chip has lots of potential (it won't be drawing much of what won't ever be seen).
 
Last edited:
Top