|This article needs additional citations for verification.|
Please help improve this article by adding reliable references. Unsourced material may be challenged and removed.(December 2009)
Larrabee is the codename for a GPGPU chip that Intel is developing separately from its current line of integrated graphics accelerators. The chip was to be released in 2010 as the core of a consumer 3D graphics card, but these plans were cancelled due to delays and disappointing early performance figures. Larrabee will now be released as a platform for research and development in computer graphics and HPC. A future version of Larrabee may eventually power a consumer graphics card, but Intel has not discussed specific plans. The name Larrabee is rumored to have come from Larrabee State Park in Washington.
Comparison with competing products
Larrabee can be considered a hybrid between a multi-core CPU and a GPU, and has similarities to both. Its coherent cache hierarchy and x86 architecture compatibility are CPU-like, while its wide SIMD vector units and texture sampling hardware are GPU-like.
As a GPU, Larrabee will support traditional rasterized 3D graphics (Direct3D & OpenGL) for games. However, Larrabee's hybrid of CPU and GPU features should be suitable for general purpose GPU (GPGPU) or stream processing tasks. For example, Larrabee might perform ray tracing or physics processing, in real time for games or offline for scientific research as a component of a supercomputer.
DreamWorks Animation has partnered with Intel and is planning to use Larrabee in movie production. DreamWorks Animation CEO Jeffrey Katzenberg states "we are well on the way of upgrading our software to really take advantage of Larrabee and in terms of speed, flexibility, capacity, it just raises the bar of what we can do by not 2 or 3x, but 20x."
Larrabee's early presentation has drawn some criticism from GPU competitors. At NVISION 08, an Nvidia employee called Intel's SIGGRAPH paper about Larrabee "marketing puff" and quoted a blogger (Peter Glaskowsky) who speculated that the Larrabee architecture was "like a GPU from 2006". As of June 2009, prototypes of Larrabee have been claimed to be on par with the Nvidia GeForce GTX 285. Justin Rattner, Intel CTO, delivered a keynote at the Supercomputing 2009 conference on November 17, 2009. During his talk he demonstrated an overclocked Larrabee processor topping one TeraFLOPS in performance. He claimed this was the first public demonstration of a single chip solution exceeding one TeraFLOPS. He pointed out this was early silicon thereby leaving open the question on eventual performance for Larrabee. Because this was only one fifth that of available competing graphics boards, Larrabee was cancelled "as a standalone discrete graphics product" on December 4, 2009.
Differences with current GPUs
- Larrabee will use the x86 instruction set with Larrabee-specific extensions.
- Larrabee will feature cache coherency across all its cores.
- Larrabee will include very little specialized graphics hardware, instead performing tasks like z-buffering, clipping, and blending in software, using a tile-based rendering approach.
This makes Larrabee more flexible than current GPUs, allowing more differentiation in appearance between games or other 3D applications. Intel's SIGGRAPH 2008 paper mentions several rendering features that are difficult to achieve on current GPUs: render target read, order-independent transparency, irregular shadow mapping, and real-time raytracing.
Although Larrabee is significantly more flexible than current GPUs, next-generation GPUs (ATI's Radeon HD 5xxx and Nvidia's GeForce 300 Series) feature increasingly broad general-purpose computing capabilities via DirectX11 DirectCompute and OpenCL, as well as Nvidia's proprietary CUDA technology.
Differences with CPUs
- Larrabee's x86 cores will be based on the much simpler Pentium P54C design which is still being maintained for use in embedded applications. The P54C-derived core is superscalar but does not include out-of-order execution, though it has been updated with modern features such as x86-64 support, similar to Intel Atom. In-order execution means lower performance for individual cores, but since they are smaller, more can fit on a single chip, increasing overall throughput. Execution is also more deterministic so instruction and task scheduling can be done by the compiler.
- Each Larrabee core contains a 512-bit vector processing unit, able to process 16 single precision floating point numbers at a time. This is similar to, but four times larger than, the SSE units on most x86 processors, with additional features like scatter/gather instructions and a mask register designed to make using the vector unit easier and more efficient. Larrabee derives most of its number-crunching power from these vector units.
- Larrabee includes one major fixed-function graphics hardware feature: texture sampling units. These perform trilinear and anisotropic filtering and texture decompression.
- Larrabee has a 1024-bit (512-bit each way) ring bus for communication between cores and to memory. This bus can be configured in two modes to support Larrabee products with 16 cores or more, or even fewer than 16 cores.
- Larrabee includes explicit cache control instructions to reduce cache thrashing during streaming operations which only read/write data once. Explicit prefetching into L2 or L1 cache is also supported.
- Each core supports 4-way simultaneous multithreading, with 4 copies of each processor register.
Theoretically Larrabee's x86 processor cores will be able to run existing PC software, or even operating systems. However, Larrabee's video card will not include all the features of a PC-compatible motherboard, so PC operating systems and applications will not run without modifications. A different version of Larrabee might sit in motherboard CPU sockets using QuickPath, but Intel has not yet announced plans for this. Though Larrabee Native's C/C++ compiler includes auto-vectorization and many applications can execute correctly after recompiling, maximum efficiency may require code optimization using C++ vector intrinsics or inline Larrabee assembly code. However, as in all GPGPU, not all software benefits from utilization of a vector processing unit. One tech journalism site claims that Larrabee graphics capabilities are planned to be integrated in CPUs based on the Haswell microarchitecture.
Comparison with the Cell Broadband Engine
Larrabee's philosophy of using many small, simple cores is similar to the ideas behind the Cell processor. There are some further commonalities, such as the use of a high-bandwidth ring bus to communicate between cores. However, there are many significant differences in implementation which should make programming Larrabee simpler.
- The Cell processor includes one main processor which controls many smaller processors. Additionally, the main processor can run an operating system. In contrast, all of Larrabee's cores are the same, and the Larrabee is not expected to run an OS.
- Each computer core in the Cell (SPE) has a local store, for which explicit (DMA) operations are used for all accesses to DRAM. Ordinary reads/writes to DRAM are not allowed. In Larrabee, all on-chip and off-chip memories are under automatically-managed coherent cache hierarchy, so that its cores virtually share a uniform memory space through standard copy (MOV) instructions. Larrabee cores each have 256K of local L2 cache, and an access which hits another L2 segment takes longer to access.
- Because of the cache coherency noted above, each program running in Larrabee has virtually a large linear memory just as in traditional general-purpose CPU; whereas an application for Cell should be programmed taking into consideration limited memory footprint of the local store associated with each SPE (for details see this article) but with theoretically higher bandwidth. However, since local L2 is faster to access, an advantage can still be gained from using Cell-style programming methods.
- Cell uses DMA for data transfer to/from on-chip local memories, which enables explicit maintenance of overlays stored in local memory to bring memory closer to the core and reduce access latencies, but requiring additional effort to maintain coherency with main memory; whereas Larrabee uses a coherent cache with special instructions for cache manipulation (notably cache eviction hints and pre-fetch instructions), which mitigate miss and eviction penalties and reduce cache pollution (e.g. for rendering pipelines and other stream-like computation) at the cost of additional traffic and overhead to maintain cache coherency.
- Each compute core in the Cell runs only one thread at a time, in-order. A core in Larrabee runs up to four threads. Larrabee's hyperthreading helps hide the latencies inherent to in-order execution.
Comparison with Intel GMA
Intel currently integrates a line of GPUs onto motherboards under the Intel GMA brand. These chips are not sold separately but are integrated onto motherboards. Though the low cost and power consumption of Intel GMA chips make them suitable for small laptops and less demanding tasks, they lack the 3D graphics processing power to compete with Nvidia and AMD/ATI for a share of the high-end gaming computer market, the HPC market, or a place in popular video game consoles. In contrast, Larrabee will be sold as a discrete GPU, separate from motherboards, and is expected to perform well enough for consideration in the next generation of video game consoles.
The team working on Larrabee is separate from the Intel GMA team. The hardware is being designed by Intel's Hillsboro, Oregon design team, whose last major design was the Nehalem. The software and drivers are being written by a newly-formed team. The 3D stack specifically is being written by developers at RAD Game Tools (including Michael Abrash).
The Intel Visual Computing Institute will research basic and applied technologies that could be applied to Larrabee-based products.
Preliminary performance data
Intel's SIGGRAPH 2008 paper describes cycle-accurate simulations (limitations of memory, caches and texture units was included) of Larrabee's projected performance. Graphs show how many 1 GHz Larrabee cores are required to maintain 60 FPS at 1600x1200 resolution in several popular games. Roughly 25 cores are required for Gears of War with no antialiasing, 25 cores for F.E.A.R with 4x antialiasing, and 10 cores for Half-Life 2: Episode 2 with 4x antialiasing. It is likely that Larrabee will run faster than 1 GHz, so these numbers do not represent actual Larrabee cores, rather virtual timeslices of such. Another graph shows that performance on these games scales nearly linearly with the number of cores up to 32 cores. At 48 cores the performance drops to 90% of what would be expected if the linear relationship continued.
A June 2007 PC Watch article suggests that the first Larrabee chips will feature 32 x86 processor cores and come out in late 2009, fabricated on a 45 nanometer process. Chips with a few defective cores due to yield issues will be sold as a 24-core version. Later in 2010 Larrabee will be shrunk for a 32 nanometer fabrication process which will enable a 48 core version.
Tech news site Fudzilla has posted several short articles about Larrabee, claiming that Larrabee may have a TDP as large as 300W,[unreliable source?] that Larrabee will use a 12-layer PCB and has a cooling system that "is meant to look similar to what you can find on high-end Nvidia cards today,"[unreliable source?] that Larrabee will use GDDR5 memory, and that it is targeted to have 2 single-precision teraflops of computing power.[unreliable source?]
The last statement of performance can be calculated (theoretically this is maximum possible performance) as follows: 32 cores × 16 single-precision float SIMD/core × 2 FLOPS (fused multiply-add) × 2GHz = 2 TFLOPS
The first public demonstration of the Larrabee architecture took place at the Intel Developer Forum in San Francisco at September 22, 2009. An early Larrabee port of the former CPU-based research project Quake Wars: Ray Traced has been shown in real-time. The scene contained a ray traced water surface that reflected the surrounding objects like a ship and several flying vehicles accurately.
The second demo was given at the SC09 conference in Portland at November 17, 2009 during a keynote by Intel CTO Justin Rattner. A Larrabee card was able to achieve 1006 GFLops in the SGEMM 4Kx4K calculation.
On December 4th, 2009, Intel officially announced that the first-generation Larrabee will not be released as a consumer GPU product. Instead, it will be released as a development platform for graphics and high-performance computing. The official reason for the strategic reset was attributed to delays in hardware and software development. Intel stated that it will announce further updates to the Larrabee project in 2010.
- ↑ 1.0 1.1 http://news.cnet.com/8301-13924_3-10409715-64.html
- ↑ http://arstechnica.com/hardware/news/2009/12/intels-larrabee-gpu-put-on-ice-more-news-to-come-in-2010.ars
- ↑ Stokes, Jon. "Intel picks up gaming physics engine for forthcoming GPU product". Ars Technica. http://arstechnica.com/news.ars/post/20070917-intel-picks-up-gaming-physics-engine-for-forthcoming-gpu-product.html. Retrieved 2007-09-17.
- ↑ Stokes, Jon. "Clearing up the confusion over Intel's Larrabee". Ars Technica. http://arstechnica.com/articles/paedia/hardware/clearing-up-the-confusion-over-intels-larrabee.ars. Retrieved 2007-06-01.
- ↑ "Intel, DreamWorks take 3D graphics to Super Bowl". January 29, 2009. http://news.cnet.com/8301-1001_3-10152355-92.html. Retrieved 2009-12-05.
- ↑ Larrabee performance--beyond the sound bite
- ↑ Intel's 'Larrabee' on Par With GeForce GTX 285
- ↑ 8.00 8.01 8.02 8.03 8.04 8.05 8.06 8.07 8.08 8.09 8.10 8.11 8.12 8.13 8.14 "Larrabee: A Many-Core x86 Architecture for Visual Computing". Intel. doi:10.1145/1360612.1360617. http://software.intel.com/file/2824/. Retrieved 2008-08-06.
- ↑ "Intel's Larrabee GPU based on secret Pentagon tech, sorta [Updated"]. Ars Technica. http://arstechnica.com/news.ars/post/20080708-intels-larrabee-gpu-based-on-secret-pentagon-tech-sorta.html. Retrieved 2008-08-06.
- ↑ Glaskowsky, Peter. "Intel's Larrabee--more and less than meets the eye". CNET. http://news.cnet.com/8301-13512_3-10006184-23.html. Retrieved 2008-08-20.
- ↑ Stokes, Jon. "Clearing up the confusion over Intel's Larrabee, part II". Ars Technica. http://arstechnica.com/news.ars/post/20070604-clearing-up-the-confusion-over-intels-larrabee-part-ii.html. Retrieved 2008-01-16.
- ↑ http://www.semiaccurate.com/2009/08/19/intel-use-larrabee-graphics-cpus/
- ↑ Chris Leyton (2008-08-13). "Intel's Larrabee Shaping Up For Next-Gen Consoles?". http://www.totalvideogames.com/news/Intels_Larrabee_Shaping_Up_For_Next-Gen_Consoles_13643_6321_0.htm. Retrieved 2008-08-24.
- ↑ Charlie Demerjian (2009-02-05). "Intel Will Design Playstation 4 GPU". http://www.theinquirer.net/inquirer/news/1050851/intel-design-playstation-gpu. Retrieved 2009-08-28.
- ↑ AnandTech: Intel's Larrabee Architecture Disclosure: A Calculated First Move
- ↑ Ng, Jansen (2009-05-13). "Intel Visual Computing Institute Opens, Will Spur "Larrabee" Development". DailyTech. http://www.dailytech.com/Intel+Visual+Computing+Institute+Opens+Will+Spur+Larrabee+Development/article15115.htm. Retrieved 2009-05-13.
- ↑ Steve Seguin (August 20, 2008). "Intel's 'Larrabee' to Shakeup AMD, Nvidia". Tom's Hardware. http://www.tomshardware.com/news/intel-larrabee-idf,6210.html. Retrieved 2008-08-24.
- ↑ "Intel is promoting the 32 core CPU "Larrabee"". pc.watch.impress.co.jp. http://pc.watch.impress.co.jp/docs/2007/0611/kaigai364.htm. Retrieved 2008-08-06. (Japanese)translation
- ↑ "Larrabee to launch at 300W TDP". fudzilla.com. http://www.fudzilla.com/index.php?option=com_content&task=view&id=7651&Itemid=1. Retrieved 2008-08-06.
- ↑ "Larrabee will use a 12-layer PCB". fudzilla.com. http://www.fudzilla.com/index.php?option=com_content&task=view&id=8435&Itemid=1. Retrieved 2008-08-06.
- ↑ "Larrabee will use GDDR5 memory". fudzilla.com. http://www.fudzilla.com/index.php?option=com_content&task=view&id=8460&Itemid=1. Retrieved 2008-08-06.
- ↑ http://arstechnica.com/hardware/news/2009/12/intels-larrabee-gpu-put-on-ice-more-news-to-come-in-2010.ars
- ↑ http://www.anandtech.com/weblog/showpost.aspx?i=659
- Video of a raytracer running on one of the first Larrabee cards at IDF '09
- Whitepapers on LRBni, Physics Simulations and more using Larrabee
- Rasterization on Larrabee
- A First Look at the Larrabee New Instructions (LRBni)
- C++ implementation of the Larrabee new instructions
- Game Physics Performance on Larrabee
- Intel fact sheet about Larrabee
- Intel's SIGGRAPH 2008 paper on Larrabee
- Techgage.com - Discusses how Larrabee differs from normal GPUs, includes block diagram illustration
- Intel's Larrabee Architecture Disclosure: A Calculated First Move