March madness isn’t just about basketball
Technology matters in March at SXSW, GDC and GTC
GTC: Nvidia’s evolution takes it into new territory with new customers and competitors
It’s ten years since Nvidia launched the GPU Technology Conference (albeit under a different name) to promote the use of their technology. This year, they are claiming an attendance of more than 8000 delegates along with one of the largest press and analyst delegations you will see outside of behemoths like CES and MWC. What started as a bold statement … Read more
GDC: Five guys and Jon: Torching the cat
The Machine Learning for Games panel (GDC, 21st March), hosted by Imagination Technologies and moderated by our very own Dr. Peddie, gave us a pretty good sense of where we are on some parts of that topic, as well as an indication that we need to be very careful to define terms. Panel mambers represented mobile, desktop, and console gaming. … Read more
JPR predicts we could have real time ray tracing on our PCs in less than 6 years
Nvidia demonstrated real-time raytracing at GDC and again at GTC using their DGX station super computer through the DirectX Raytracing (DXR) API. That system provides a theoretical compute capability of over 63 TFLOPS for the total system, of which about 62 TFLOPS were used for the ray tracing. So a threshold or benchmark of sorts has been established for what … Read more
JPR predicts we could have real time ray tracing on our PCs in less than 6 years
Nvidia demonstrated real-time raytracing at GDC and again at GTC using their DGX station super computer through the DirectX Raytracing (DXR) API. That system provides a theoretical compute capability of over 63 TFLOPS for the total system, of which about 62 TFLOPS were used for the ray tracing. So a threshold or benchmark of sorts has been established for what … Read more
JPR predicts we could have real time ray tracing on our PCs in less than 6 years
It will take a little longer for smartphones Nvidia demonstrated Microsoft’s approach to raytracing for games at GDC and again at GTC using their DGX station super computer through the DXR API. The $50,000 DGX contains four NVLink 4-Way interconnected Nvidia Tesla V100 add-in boards (AIBs). Each AIB has a 5,120-shader Volta GPU running at 1.46 GHz with 16 GB … Read more
Hey buddy, wanna buy a cheap super computer?
After alerting the media at the Supercomputing Conference in 2016, Nvidia introduced the DGX-1 supercomputer at GTC 2016, as the world's first deep learning supercomputer to meet the unlimited computing demands of artificial intelligence. The price was $149,000 and came equipped with eight Tesla V100s GPUs, linked together via next-gen Nvidia NVLink interconnect technology that ups the bandwidth per GPU … Read more
Nvidia claims real time ray tracing now possible
At GDC, Nvidia and Microsoft made a joint announcement about the possibility of doing real time ray tracing, something the CG community has striven for since ray tracing was popularized by Turner Whitted in 1979. Whitted did it on big computers at Bell Labs, just before the PC was introduced. Since then, scores of papers and books have been written … Read more
Nvidia claims realtime ray tracing now possible
Using AI techniques, and powerful processor
Major new versions of SPECviewperf coming on its 30th anniversary
Major versions of SPECviewperf and SPECwpc (to be renamed SPECworkstation) are on tap for Q2 of this year. SPECviewperf 13 will feature new volume visualization viewsets for energy and medical applications, radically new shaders, and updated viewsets to match more recent versions of the applications on which they are based. SPECworkstation 3.0 will include new GPU performance measurement, completely redesigned … Read more
SPEC celebrates 30th anniversary with SPECviewperf update
Expanded SPECworkstation benchmark slated for Q2
Khronos’ Vulkan 1.1 API has added functionality
More of a computing device than a graphics processor now? Khronos has just released version 1.1 of its high-performance GPU API, Vulkan. The heir apparent to OpenGL, and OpenGL ES, this thin and light API exposes the many features and benefits of a modern GPU like no other API and takes it into the GPU compute domain with a new … Read more