News
 

Bookmark and Share

(10) 

At the Intel Developer Forum 2011, Intel Corp. showcased a system running a new version of its real-time “Wolfenstein” ray-tracing demo. In order to render the game scenes in full HD (1080p) resolution and with additional visual effects, Intel had to use a 2-way Xeon system with eight code-named Knights Ferry compute accelerators.

The up-to-date Wolfenstein game is rendered through a real-time ray tracer with several special effects that haven’t been possible before in games with such an accuracy. The latest Wolfenstein game demo also includes such effects as depth of field, HDR bloom, inter-lens reflection, smart anti-aliasing.

Las year Intel rendered Wolfenstein demo using a “cloud” of four Intel's Knights Ferry/Aubrey Isle compute accelerate cards in 720p (1280*720 resolution). This year Intel decided to install eight KNF compute cards and render the demo in 1080p (resolution). As ray tracing is a highly parallel application it can therefore take very good benefit of the many cores that are in a single chip on the Knights Ferry board.

The demonstration is a proof-of-concept of real-time ray-tracing as well as many Intel core (MIC) architecture. However, the show off does not have a lot of practical meaning since real-time ray-tracing will hardly be used in the consumer applications for many years.

The Knights Ferry has 32 x86 cores clocked at 1.2GHz and featuring quad-HyperThreading. The unit, aimed at PCI Express 2.0 slots, has up to 2GB of GDDR5 memory. The chip itself has 8MB of shared L2 cache, which is quite intriguing by itself since highly-parallel applications do not require a large on-chip cache.

According to Intel, eight KNF compute boards (on 2-way Intel Xeon X5690 [3.46GHz, 6 cores, 12MB L3 cache] with 24GB DDR3 RAM at 1333MHz) achieved 7TFLOPS performance in SGEMM [single precision general matrix multiply] operations, which is not a truly high result.

Tags: Intel, Knights Ferry, Aubrey Isle, Larrabee, MIC, GPGPU

Discussion

Comments currently: 10
Discussion started: 09/14/11 07:02:10 PM
Latest comment: 09/16/11 09:43:04 AM
Expand all threads | Collapse all threads

[1-5]

1. 
AMD Cayman can produce 2.7 TFLOPs of single precision performance
2.7 Times 8 = 21.6 TFLOPs
2 2 [Posted by: blazzin  | Date: 09/14/11 07:02:10 PM]
Reply
- collapse thread

 
So you need to write a ray-tracer to 6990 to prove that Intel is wrong.
1 0 [Posted by: Tristan  | Date: 09/15/11 02:29:05 AM]
Reply
 
SGEMM is not about ray-tracing.

Apparently, actual horsepower of KNF is a well-kept secret.
0 0 [Posted by: Anton  | Date: 09/15/11 06:36:58 PM]
Reply

2. 
Intel is so far behind AMD and Nvidia in Graphics that even there fab powerhouse cant help.
3 0 [Posted by: vid_ghost  | Date: 09/15/11 02:18:55 AM]
Reply

3. 
AMD Cayman can produce 2.7 TFLOPs of single precision performance 2.7 Times 8 = 21.6 TFLOPs


That is theoretical peak performance.The same applies for CPUs.
Achieve xTFLOPS in BLAS is not theoretical peak, but actual performance I presume.
If you look at CUBLAS numbers i.e., C2050, which in double precision has around 500GFLOPs of peak performance (is comparable to Cayman in other words), in DGEMM it manages around 160GFLOPS which is already pretty high.

Look here:
http://www.microway.com/p...050-Fermi-Performance.pdf
0 0 [Posted by: dkarko  | Date: 09/15/11 02:25:00 AM]
Reply
- collapse thread

 
The smallLuxGPU demo shows that the AMD GPU gets near theoretical TFLOPS when raytracing under OpenCL.

http://www.anandtech.com/...hd-6970-radeon-hd-6950/23
1 0 [Posted by: user99  | Date: 09/15/11 12:29:14 PM]
Reply
 
I see your point but I don't see flops there. I see them saying that it is closer to theoretical than civ5 (probably based on the fact that it performed worse on civ5).

Anyway Intel saying they achieved that in some ray-tracer says nothing. KNF will have to prove itself in more wide problems in GPGPU
0 0 [Posted by: dkarko  | Date: 09/16/11 01:09:45 AM]
Reply
 
Fair Enough
0 0 [Posted by: blazzin  | Date: 09/16/11 09:43:04 AM]
Reply

4. 
Intel tries to compete in graphics,but will never succeed. Amd will mop Intel right up in graphics.
1 0 [Posted by: twainamd  | Date: 09/15/11 09:31:45 AM]
Reply

5. 
Intel wants the HPC market, where 80% is NVidia and 20% is AMD now. However, they and AMD, need SDK to get the market. AMD hopes are for Open CL to take traction.
2 0 [Posted by: Ananke  | Date: 09/15/11 12:26:45 PM]
Reply

[1-5]

Add your Comment




Related news

Latest News

Friday, May 24, 2013

6:09 pm | Second-Generation Kinect Sensor for Windows Due in 2014 – Microsoft. Microsoft Discloses Additional Details About Kinect 2

4:24 pm | New Technique May Open Up an Era of Atomic-Scale Semiconductor Devices. Atom-Scale Semiconductor Devices May Be Incoming, Thanks to New Researchers

Thursday, May 23, 2013

11:30 pm | Kinect Support Is Not Mandatory for Xbox One Video Games – Microsoft. Microsoft Will Not Require Compulsory Support of Kinect from Xbox One Games

11:20 pm | Thermaltake Publishes List of PSUs Compatible with Intel Cori i “Haswell” Chips. 20 PSUs from Thermaltake Are Compatible with Next-Gen Intel Chips

11:10 pm | European Amazon Stores Start to List Xbox One with €599 Price-Tag. Microsoft Xbox One May Cost €599 in Europe, If First Listings Are Correct

9:28 pm | Apple to Assemble Macs in Texas, Set to Manufacture Parts Across the U.S. Apple’s Plan to Move Production Back to U.S. Gets Shape

9:12 pm | Microsoft Confident in Lack of Quality Issues with Xbox One Hardware. Microsoft Vows Xbox One Will Not Have RROD-Like Issues

8:52 pm | AMD Officially Launches New-Generation APUs for Mobile Applications [UPDATED]. AMD Introduces Kabini, Temash and Richland Accelerated Processing Units

6:51 pm | OCZ Reveals Vertex 450 Solid-State Drives: High-End Performance at Mainstream Prices. OCZ Introduces New SSDs Based on Indilinx Barefoot 3 Controller

3:40 pm | Nvidia Unveils GeForce GTX 780: GK110-Based Consumer Solution for $649. Nvidia’s Cut Down Titan LE Becomes GeForce GTX 780