Matrox, along with S3, develop GPU ASICs for use with desktop add-in boards, alongside AMD and NVIDIA. Last year, they sold less than 7000 units in their quarter according to my math (rounding to 0.0% market share implies < 0.05% of total market, which was 7000 units that quarter). Today, Matrox Graphics Inc. announce that they will use an AMD GPU on their upcoming product line.
While they do not mention a specific processor, they note that "the selected AMD GPU" will be manufactured at a 28nm process with 1.5 billion transistors. It will support DirectX 11.2, OpenGL 4.4, and OpenCL 1.2. It will have a 128-bit memory bus.
Basically, it kind-of has to be Cape Verde XT (or XT GL) unless it is a new, unannounced GPU.
If it is Cape Verde XT, it would have about 1.0 to 1.2 TFLOPs of single precision performance (depending on the chosen clock rate). Whatever clock rate is chosen, the chip contains 640 shader processors. It was first released in February 2012 with the Radeon HD 7770 GHz Edition. Again, this is assuming that AMD will not release a GPU refresh for that category.
Matrox will provide their PowerDesk software to configure multiple monitors. It will work alongside AMD's professional graphics drivers. It is a sad that to see a GPU ASIC manufacturer throw in the towel, at least temporarily, but hopefully they can use AMD's technology to remain in the business with competitive products. Who knows: maybe they will make a return when future graphics APIs reduce the burden of driver and product development?
Will they be able to improve
Will they be able to improve AMD’s Linux driver support, or will they be just another after market device producer for AMD. it would be nice if they could add some hardware ray tracing ability to AMD’s GPU microarchitecture and free graphics from the tyranny of too few CPU cores, once and for all time.
Smart choice Matrox 🙂
“AMD
Smart choice Matrox 🙂
“AMD introduces new ray tracing technology”
http://gfxspeak.com/2014/08/28/introduces-tracing-technology/
Ray tracing software !=
Ray tracing software != dedicated Ray tracing hardware, that demo takes 10,200(firepro driver based($$$) expensive SKUs) GPU stream processors, so it must be using some OpenCL, or OpenCL/HSAIL type of translation and GPGPU to do the ray interaction calculations! It’s a start towards a move away from the god awful dependency on Intel’s CPUs in all graphics workloads, so yes this is a start, but the PowerVR mobile SOC GPU, has actual ray tracing hardware, and I hope that AMD and Nvidia, as well as others would get a clue, and want to get the sales! Being able to completely eliminate the CPU(Intel’s, or any others’) as a factor in professional graphics, especially the uber expensive Intel Xeons, would mean more money for the GPU massively parallel processing of ray interactions(in dedicated hardware) and a huge time savings for graphics workflows. Just price a powerful workstation CPU, that still takes a lot of time to do intensive ray tracing calculations, and see that doing away with the CPU as a necessary cost in graphics, frees up billions of dollars, pounds, calms/whatever, to be spent on the GPU SKUs that should come with massively parallel ray tracing units, at least for the professional SKUs, and maybe even the gaming SKUs! Imagination, the makers of the PowerVR wizard(hardware ray tracing), and the MIPS warrior CPU, should seriously consider making a discrete professional GPU product with its hardware ray tracing and GPU cores expanded for a discrete desktop SKU, Nvidia has no problem basing its Kepler/Maxwell microarchitecture on a ramped up to desktop from mobile, or a ramped down to from desktop to mobile, Unified GPU microarchitecture. Imagine portable workstations, and laptops, that would only need inexpensive CPUs, because the Ray Tracing calculations, would be done in a massively parallel manner on the GPU’s dedicated ray tracing circuitry.