That's also described as concurrent execution of FP32 and INT32 operation. The Turing SM architecture supports parallel execution of FP32 and INT32 operations, independent thread scheduling similar to the Volta GV100 GPU.
Now before you get all confused, yes, that is radically different from Pascal (GeForce series 1000) which had one SM per TPC and 128 FP32 Cores per SM. Each SM has a total of 64 FP32 Cores and 64 INT32 Cores. Two SMs are included per TPC (Texture / Processor Cluster - a group made up of several SMs). As I mentioned, it has a bit of everything, but mostly it hints towards Volta. We'll try and be brief here, but Turing is a new and completely overhauled architecture that actually has gotten a new SM (Streaming Multiprocessor) design. We've placed the main specifications in a table overview.
The GPU TU106 for the GeForce RTX 2060 Super is the same, yet cut down, it has 34 SMs (streaming multiprocessors) each holding 64 cores = 2176 Shader processors.
This GPU is fabbed on an optimized 12nm TSMC FinFET+ node and the full GPU is unlocked. Gamers will immediately look at the shader processors, the Quadro RTX 80 of them enabled and, since everything with bits is in multitudes of eight, while looking at the GPU die photos a TU104 based GeForce RTX 2070 Super has 40 SMs (streaming multiprocessors) each holding 64 cores = 2560 Shader processors. In comparison, Pascal had close to 12 billion transistors on a die size of 471mm2. It's fabbed at 12nm FFN.Īs mentioned, the RTX 20 (Super) cards make use of the TU106 which contains 10.8 billion transistors localized onto the 455mm2 die. In essence, the TU106 is the more simplified revision of the TU102, but shares its architecture. The RTX 2080 uses the TU104, the RTX 2060 TU1 SUPER also TU104. Bear in mind that the base building block for all Turing GPUs will be the TU102, that is the flagship GPU that has been used on the GeForce RTX 2080 Ti. Looking at the Turing GPU, there is a lot of stuff you can recognize, but starting at Turing there certainly have been fundamental block changes in the architecture the SM (Streaming Multiprocessor) clusters have separated, and now are core separated isolated blocks.