Intel Xe

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Intel Xe
Intel Iris Xe Graphics (logo).svg
Release dateSeptember 2, 2020 (2020-09-02)
Entry-levelIris Xe Graphics
High-endIntel Arc
PredecessorGen 11
SuccessorIntel Xe 2

Intel Xe (stylized as Xe and pronounced as two separate letters,[1] abbreviation for "eXascale for everyone"[2]), earlier known unofficially as Gen12,[3][4] is a GPU architecture developed by Intel.[5]

Intel Xe includes a new instruction set architecture. The Xe GPU family consists of a series of microarchitectures, ranging from integrated/low power (Xe-LP),[6] to enthusiast/high performance gaming (Xe-HPG), datacenter/high performance (Xe-HP) and high performance computing (Xe-HPC).[7][8]


Intel's first attempt at a dedicated graphics card was the Intel740,[9] released in February 1998. The Intel740 was considered unsuccessful due to its performance which was lower than market expectations, causing Intel to cease development on future discrete graphics products. However, its technology lived on in the Intel Extreme Graphics lineup.[10] Intel made another attempt with the Larrabee architecture before cancelling it in 2009;[11] this time, the technology developed was used in the Xeon Phi, which was discontinued in 2020.[12]

In April 2018, it was reported that Intel was assembling a team to develop discrete graphics processing units, targeting both datacenters, as well as the PC gaming market, and therefore competitive with products from both Nvidia and AMD.[13] Rumors supporting the claim included that the company had vacancies for over 100 graphics-related jobs, and had taken on former Radeon Technologies Group (AMD) leader Raja Koduri in late 2017 – the new product was reported to be codenamed "Arctic Sound".[13] The project was reported to have initially been targeting video streaming chips for data centers, but had its scope expanded to include desktop GPUs.[13]

In June 2018, Intel confirmed it planned to launch a discrete GPU in 2020.[14]

The first functional discrete "Xe" GPU, codenamed "DG1", was reported as having begun testing in October 2019.[15]

According to a report by in late 2019, a discrete GPU would launch in mid 2020; combined GPU/CPU (GPGPU) products were also expected, for data center and autonomous driving applications. The product is expected to be initially built on a 10 nm node (with 7 nm products in 2021) and use Intel's Foveros die stacking packaging technology (see 3D die stacking).[16]


Intel Xe expands upon the microarchitectural overhaul introduced in Gen 11 with a full refactor of the instruction set architecture.[17][4] While Xe is a family of architectures, each variant has significant differences from each other as these are made with their targets in mind. The Xe GPU family consists of Xe-LP, Xe-HP, Xe-HPC, and Xe-HPG sub-architectures.

Unlike previous Intel graphics processing units which used the Execution Unit (EU) as a compute unit, Xe-HPG and Xe-HPC use the Xe-core.[18] This is similar to an Xe-LP subslice.[18] An Xe-core contains vector and matrix arithmetic logic units, which are referred to as vector and matrix engines. Other components include L1 cache and other hardware.[18][19]

Xe-LP (Low Power)[edit]

Xe-LP is the low power variant of the Xe architecture.[6] Xe-LP is present as integrated graphics for 11th-generation Intel Core and the Iris Xe MAX mobile dedicated GPU (codenamed DG1), as well as in the H3C XG310 Intel Server GPU (codenamed SG1).[4] Compared to its predecessor, Xe-LP includes new features such as Sampler Feedback,[20] Dual Queue Support,[21] DirectX12 View Instancing Tier2,[22] and AV1 8-bit and 10-bit fixed-function hardware decoding.[23]

Xe-HP (High Performance)[edit]

Xe-HP is the datacenter/high performance variant of Xe, optimized for FP64 performance and multi-tile scalability.[5]

Xe-HPC (High Performance Compute)[edit]

Xe-HPC is the high performance computing variant of the Xe architecture.[7][8] An Xe-HPC Xe-core contains 8 vector and 8 matrix engines, alongside a large 512 KB L1 cache.[24] It powers Ponte Vecchio.

Xe-HPG (High Performance Graphics)[edit]

Xe-HPG is the enthusiast or high performance graphics variant of the Xe architecture. The microarchitecture is based on Xe-LP with improvements from Xe-HP and Xe-HPC.[25] The microarchitecture is focused on graphics performance and supports hardware-accelerated ray tracing,[7][26] DisplayPort 2.0,[27] XeSS or supersampling based on neural networks (similar to Nvidia DLSS), and DirectX 12 Ultimate. [28] Intel confirmed ASTC support has been removed from hardware starting with Alchemist and future Intel Arc GPU microarchitectures will also not support it.[29] An Xe-HPG Xe-core contains 16 vector engines and 16 matrix engines.[19] An Xe-HPG render slice will consist of four Xe-cores, ray tracing hardware, and other components.[19]

Intel Xe 2[edit]

Intel Xe 2
Release date2023
PredecessorIntel Xe
SuccessorIntel Xe 3

A successor to Xe was revealed during Intel Architecture Day 2021, under the name of Xe 2, codenamed Battlemage. It is currently under development.[19]

Intel Xe 3[edit]

Intel Xe 3
Release date2024
PredecessorIntel Xe 2

Intel Xe 3 is the upcoming successor to the Intel Xe 2 microarchitecture codenamed Celestial and is scheduled for a 2024 release as per Intel's GPU roadmap.[19]

Intel Xe 4[edit]

Intel Xe 4
PredecessorIntel Xe 3

Intel Xe 4 is the upcoming successor to the Intel Xe 3 microarchitecture codenamed Druid.[30]

Products using Xe[edit]

Integrated graphics[edit]

Newer Intel processors use the Xe-LP microarchitecture. These include 11th generation Intel Core processors (codenamed "Tiger Lake" and "Rocket Lake"),[4] 12th generation Intel Core processors (codenamed "Alder Lake") and future 13th generation Intel Core processors (codenamed "Raptor Lake") set to release in H2 2022.

Discrete graphics[edit]

Intel Iris Xe Max (DG1)[edit]

Model Launch Process Execution




Clock speeds Memory Processing power (GFLOPS) Notes
Boost clock










Bus width


Half Single Double INT8
Iris Xe MAX November 1, 2020 Intel 10SF 96 768 1650 4266 4 68 LPDDR4x 128 5069 2534 1267 10138  

In August 2020, Intel was reported to be shipping Xe DG1 GPUs for a possible late 2020 release, while also commenting on a DG2 GPU aimed at the enthusiast market. The DG1 is also sold as the Iris Xe MAX and as Iris Xe Graphics (stylized as iRIS Xe) in laptops, while cards for developers are sold as the DG1 SDV.[31][32]

The Xe MAX is an entry-level GPU that was first released on November 1, 2020 in China and is similar in most aspects to the integrated GPU found in Tiger Lake processors, the only differences being a higher clock speed, slightly higher performance and dedicated memory and a dedicated TDP requirement. It competes with Nvidia's laptop-level GeForce MX series GPUs. It is aimed at slim and highly portable productivity laptops and has 4GB of dedicated LPDDR4X-4266 memory with a 128-bit wide memory bus, has 96 EUs, 48 texture units, 24 ROPs, a peak clock speed of 1650 MHz and a performance of 2.46 FP32 teraFLOPs with a 25w TDP. By comparison, the integrated GPU in Tiger Lake processors has a performance of 2.1 FP32 teraFLOPs.[33][34] The Xe MAX does not replace the system's integrated GPU; instead it was designed to work alongside it, so tasks are split between the integrated and discrete GPUs.[35] It was initially available on only 3 laptops: The Asus VivoBook Flip 14 TP470, the Acer Swift 3X, and the Dell Inspiron 15 7000. Intel Xe MAX GPUs can only be found on systems with Tiger Lake processors.

Intel officially announced Intel Iris Xe Graphics desktop cards for OEMs and system integrators on January 26, 2021. It is aimed at mainstream desktop and business PCs as an improvement over other graphics options in AV1 video decoding, HDR (high dynamic range) video support and deep learning inference, and is not as powerful as its laptop counterpart, with only 80 enabled EUs. The first cards are made by Asus, have DisplayPort 1.4, HDMI 2.0, Dual Link DL-DVI-D outputs and are passively cooled.[36][37][38][39]

Intel Arc[edit]

Intel Arc is a high-performance discrete graphics line optimized for gaming. This will compete directly with the AMD Radeon and Nvidia GeForce lines of graphics processing units. The first generation (codenamed "Alchemist"), was developed under the "DG2" name and is based on the Xe-HPG architecture. Future generations are codenamed Battlemage ("DG3", based on Xe2), Celestial ("DG4", based on Xe3), and Druid ("DG5").


According to Intel's roadmap the release of Arc 5/Arc 7 desktop graphics cards is scheduled for Q2 or Q3 2022.

GPU Branding Model Launch Code name (s) Process (nm) Transistors (billion) Die size (mm) Core Config (Shading units:TMU:ROP:RT core) Execution


L2 Cache (MB) Clock speeds Fillrate Memory Processing power (TFLOP) TDP Bus interface
Boost clock




Pixel (GP/s) Texture






Type Bus width


Half Single Double
Arc 3 A380 June 14, 2022 DG2-128 TSMC N6 7.2 157 1024:64:32:8 128 4 2000 14000 64 128 6 186 GDDR6 96 8.192 4.096 1.024 75w PCIe 4.0 x8
Model[40] Launch Code name(s) Process (nm) Transistors (billion) Die size
Core config EU
L2 cache
Clock speeds Fillrate Memory Processing power (TFLOPS) TDP (watts) Bus
Core clock MHz


Memory (MT/s) Pixel
Size (GB) Bandwidth (GB/s) Type Bus width (bit) Half precision (boost) Single precision (boost) Double precision (boost)
Arc 3 A350M March 30, 2022 DG2-128 TSMC N6 7.2 157 768:48:24:6 96 4 300 (1150) 14000 27.6 55.2 4 112 GDDR6 64 ? (3.533) ? (1.766) ? (0.441) 25-35 PCIe 4.0 x8
A370M 1024:64:32:8 128 300 (1550) 49.6 99.2 ? (6.349) ? (3.174) ? (0.793) 35-50
Arc 5 A550M Q2 2022 DG2-512 21.7 406 2048:128:64:16 256 8 300 (900) 57.6 115.2 8 224 128 ? (7.373) ? (3.686) ? (0.921) 60-80 PCIe 4.0 x16
Arc 7 A730M 3072:192:96:24 384 12 300 (1100) 105.6 211.2 12 336 192 ? (13.52) ? (6.758) ? (1.69) 80-120
A770M 4096:256:128:32 512 16 300 (1650) 16000 211.2 422.4 16 512 256 ? (27.03) ? (13.52) ? (3.379) 120-150


Ponte Vecchio[edit]

Intel officially announced their Xe general HPC/AI GPU codenamed Ponte Vecchio on November 17, 2019. It was revealed to use the Xe-HPC variant of the architecture[41] and Intel's 'Embedded Multi-Die Interconnect Bridge' (EMIB) and Foveros die stacking packaging on a Intel 4 node (previously referred to as 7 nm). Intel later confirmed at Architecture Day 2021 that Ponte Vecchio would use Compute Tiles manufactured on TSMC N5, Base Tiles and Rambo Cache Tiles manufactured using Intel 7 (previously referred to as 10 nm Enhanced SuperFin) and Xe Link Tiles manufactured on the TSMC N7 process. The new GPU is expected to be used in Argonne National Laboratory's new exascale supercomputer, Aurora, with compute nodes comprising two next generation Intel Xeon (codenamed "Sapphire Rapids") CPUs, and six Ponte Vecchio GPUs.[42][43]

Rialto Bridge[edit]

Intel officially announced the successor to Ponte Vecchio, GPU codenamed Rialto Bridge on May 31, 2022.[44]

See also[edit]


  1. ^ How to Pronounce Intel's Xe (Xe) and Ponte Vecchio, 15 August 2020
  2. ^ Raja Koduri on Twitter, 18 March 2019
  3. ^ Cutress, Ian (12 December 2018), "Intel's Architecture Day 2018: The Future of Core, Intel GPUs, 10nm, and Hybrid x86",, p. 5, Intel will use the Xe branding for its range of graphics that were unofficially called 'Gen12' in previous discussions
  4. ^ a b c d Hill, Brandon (9 Sep 2019), "Intel Says Tiger Lake Gen12 Xe Graphics Is Its Biggest Architectural Revamp In A Decade",
  5. ^ a b Smith, Ryan. "The Intel Xe-LP GPU Architecture Deep Dive: Building Up The Next Generation". Retrieved 2021-04-10.
  6. ^ a b Salter, Jim (2020-11-04). "Intel enters the laptop discrete GPU market with Xe Max". Ars Technica. Retrieved 2021-04-10.
  7. ^ a b c Smith, Ryan. "Intel's Xe-HPG GPU Unveiled: Built for Enthusiast Gamers, Built at a Third-Party Fab".
  8. ^ a b Alderson, Alex. "The Intel Xe-HP NEO hits Geekbench with 512 compute units, 4,096 shading units and 6 GB of HBM2 VRAM". Notebookcheck. Retrieved 2021-04-10.
  9. ^ Hollister, Sean (January 9, 2020). "This is Intel's first discrete graphics card in 20 years, but you can't buy one". The Verge.
  10. ^ "Evolution Of Intel Graphics: i740 To Iris Pro | Tom's Hardware". 4 February 2017.
  11. ^ "Intel scraps graphics chip based on Larrabee". Reuters. December 6, 2009 – via
  12. ^ "Intel Quietly Kills Off Xeon Phi - ExtremeTech".
  13. ^ a b c Evangelho, Jason (11 Apr 2018), "Intel Is Developing A Desktop Gaming GPU To Fight Nvidia, AMD",
  14. ^ Hill, Brandon (12 June 2018), "Intel To Power Up Its First Discrete GPU Confirmed For 2020 Launch",
  15. ^ Allan, Darren (26 Oct 2019), "Intel's first Xe graphics card is officially 'alive' and coming for AMD and Nvidia",
  16. ^ Tyson, Mark (16 Oct 2019), "Industry sources say discrete Intel Xe cards will arrive mid-2020",
  17. ^ Smith, Ryan. "The Intel Xe-LP GPU Architecture Deep Dive: Building Up The Next Generation". p. 3. Retrieved 2022-07-29.
  18. ^ a b c Smith, Ryan. "Intel Architecture Day 2021: A Sneak Peek At The Xe-HPG GPU Architecture". Retrieved 2021-08-29.
  19. ^ a b c d e Cunningham, Andrew (2021-08-20). "Intel provides more details on its Arc GPUs, which will be made by TSMC". Ars Technica. Retrieved 2021-08-29.
  20. ^ "DirectX12 Sampler Feedback". Intel.
  21. ^ "Dual Queue Support". Intel.
  22. ^ "DirectX12 View Instancing and Vulkan Multiview". Intel.
  23. ^ "AV1 Hardware Accelerated Video on Windows 10". TECHCOMMUNITY.MICROSOFT.COM. October 9, 2020.
  24. ^ Cutress, Dr Ian. "Hot Chips 2021 Live Blog: Graphics (Intel, AMD, Google, Xilinx)". Retrieved 2021-08-29.
  25. ^ "Intel Introduces New High-Performance Graphics Brand: Intel Arc".
  26. ^ "Intel Xe graphics: Everything you need to know about Intel's dedicated GPUs". 17 March 2021. Retrieved 2021-04-10.{{cite web}}: CS1 maint: url-status (link)
  27. ^
  28. ^ Smith, Ryan. "Intel Video Cards Get a Brand Name: Arc, Starting with "Alchemist" in Q1 2022". AnandTech. Retrieved 2021-08-29.
  29. ^ "Intel: ASTC support was removed on Gfx12.5 (!13206) · Merge requests · Mesa / Mesa".
  30. ^ "Intel Arc A750 GPU Hands-On, Driver Challenges, & Overclocking". YouTube.
  31. ^ "Intel Xe DG1 GPU is shipping and will release this year". TechSpot. Retrieved 2021-02-14.
  32. ^ Mujtaba, Hassan (2020-01-09). "Intel's First Xe DG1 GPU Based Desktop Discrete Graphics Card Pictured". Wccftech. Retrieved 2021-02-14.
  33. ^ Smith, Ryan. "Intel's Discrete GPU Era Begins: Intel Launches Iris Xe MAX For Entry-Level Laptops". Retrieved 2021-02-14.
  34. ^ "Intel Launches New Xe Max Mobile GPUs for Entry-Level Content Creators - ExtremeTech". Retrieved 2021-02-14.
  35. ^ Salter, Jim (2020-11-04). "Intel enters the laptop discrete GPU market with Xe Max". Ars Technica. Retrieved 2021-02-14.
  36. ^ "Intel Releases Iris Xe Desktop Graphics Cards". Intel Newsroom. Retrieved 2021-02-14.
  37. ^ "Intel Iris Xe Graphics—Dedicated GPU for PCs". Intel. Retrieved 2021-02-14.
  38. ^ "Intel Iris Xe Dedicated Graphics Card (80 EU) Product Specifications".
  39. ^ Smith, Ryan. "Intel Iris Xe Video Cards Now Shipping To OEMs: DG1 Lands In Desktops". Retrieved 2021-02-14.
  40. ^ "Intel Arc Graphics". Intel.
  41. ^ Smith, Ryan. "Intel Teases Ponte Vecchio Xe-HPC Power On, Posts Photo of Server Chip". Retrieved 2021-04-10.
  42. ^ Intel Unveils New GPU Architecture with High-Performance Computing and AI Acceleration, and oneAPI Software Stack with Unified and Scalable Abstraction for Heterogeneous Architectures (press release), Intel, 17 Nov 2019
  43. ^ Cutress, Ian (17 Nov 2019), "Intel's Xe for HPC: Ponte Vecchio with Chiplets, EMIB, and Foveros on 7nm, Coming 2021",
  44. ^ "Accelerated Innovations for Sustainable, Open HPC".