Wednesday, December 12th 2018
Intel Gen11 iGPU Roughly as Fast as Radeon Vega 8 (Ryzen 3 2200G)
Today, Intel is revealing major details about its upcoming CPU and graphics architectures to select audience. A big scoop VideoCardz landed is the company's next-generation Gen11 integrated graphics core, the first major upgrade to the company's 4-year old Gen9 architecture. According to them, a Gen11 (default GT2 trim we assume) graphics core should offer a compute throughput of 1 TFLOP/s, which is in the league of the Radeon Vega 8, with its 1.12 TFLOP/s throughput. The Vega 8 is part of AMD's Ryzen 3 2200G processor.
Raw compute power only paints half the picture, the iGPU reportedly also supports tile-based rendering. This is a highly publicized method of rendering that made its consumer debut with NVIDIA "Pascal." Also mentioned are redesigned FPU interfaces, support for half-precision FP16, 2x pixel/clock pipelines, display stream compression that lets it support 5K and 8K displays, and adaptive sync. Intel will debut its Gen11 iGPU with its upcoming Core "Ice Lake" processors that debut on the company's 10 nm silicon fabrication process.
Source:
VideoCardz
Raw compute power only paints half the picture, the iGPU reportedly also supports tile-based rendering. This is a highly publicized method of rendering that made its consumer debut with NVIDIA "Pascal." Also mentioned are redesigned FPU interfaces, support for half-precision FP16, 2x pixel/clock pipelines, display stream compression that lets it support 5K and 8K displays, and adaptive sync. Intel will debut its Gen11 iGPU with its upcoming Core "Ice Lake" processors that debut on the company's 10 nm silicon fabrication process.
37 Comments on Intel Gen11 iGPU Roughly as Fast as Radeon Vega 8 (Ryzen 3 2200G)
Edit: Anandtech has a full write-up.
www.anandtech.com/show/13699/intel-architecture-day-2018-core-future-hybrid-x86
www.anandtech.com/print/13699/intel-architecture-day-2018-core-future-hybrid-x86
Maybe we are just too old...
Earliest work on tile based rendering goes to Pixel Planes 5 architecture from 1989.
Intel HD 640 Iris Plus has 844.8 GFLOPS FP32. 16FP double rate already exist.
www.techpowerup.com/gpu-specs/iris-plus-graphics-655.c3221
Intel HD 655 Iris Plus has 921.6 GFLOPS FP32. 16FP double rate already exist.
TFLOPS argument doesn't factor in rasterzation power, early triangle culling/triangle binning and raster read/write capability.
Nvidia Maxwell already has immediate mode tile render with L2 cache. Vega introduces it's ROPS being connected to L2 cache design. Xbox One X's ROPS has 2MB render cache. Xbox One and Xbox 360 has software immediate mode tile render.
RX Vega gfx9 family has 16FP double rate already exist while Kabylake G's fake Vega is missing 16FP double rate feature.
PowerVR has deferred mode tile render.
Common, dude!
And I say this a Vega owner btw.