These instructions are most efficient when data structures are a power of two in size, and here’s a tip provided by the Maxwell Tuning Guide: In addition, the throughput of many integer operations including multiply, logical operations and shift is improved on Maxwell, and there are now specialized integer instructions that can accelerate pointer arithmetic.
The improvements to SM topology and scheduling should benefit performance as well as efficiency, and as I mentioned in my post about first-generation Maxwell, instruction latencies have been significantly reduced.īecause occupancy (which translates to available warp-level parallelism) is the same or better on SMM as on SMX, these reduced latencies improve utilization and throughput. *The GFLOPS and texel fill rates in this table are based on GPU Base Clock GPU The table shows a comparison of speeds and feeds between GeForce GTX 680 (Kepler GK104) and the new GeForce GTX 980 (Maxwell GM204). Each SMM provides eight texture units, one polymorph engine (geometry processing for graphics), and dedicated register file and shared memory. SMM uses a quadrant-based design with four 32-core processing blocks each with a dedicated warp scheduler capable of dispatching two instructions per clock. The new SMM, shown in Figure 1, includes all of the architectural benefits of its first-generation Maxwell predecessor, including i mprovements to control logic partitioning, workload balancing, clock-gating granularity, instruction scheduling, number of instructions issued per clock cycle, and more.
Maxwell’s new datapath organization and improved instruction scheduler provide more than 40% higher delivered performance per CUDA core, and overall twice the efficiency of Kepler GK104. SMM: The Maxwell Multiprocessor Figure 1: Maxwell’s Multiprocessor, SMM.Īs I discussed in my earlier Maxwell post, the heart of Maxwell’s power-efficient performance is it’s Streaming Multiprocessor, known as SMM. GM204’s 16 SMs make it over 3 times faster than the first-generation GM107 GPU that I introduced earlier this year on Parallel Forall, and additional architectural improvements help GM204 pack an even bigger punch. But of course they also make fantastic CUDA development GPUs, with full support for CUDA 6.5 and all of the latest features of the CUDA platform, including Unified Memory and Dynamic Parallelism.
The GeForce GTX 980 and 970 GPUs introduced today are the most advanced gaming and graphics GPUs ever made. GM204 is the first GPU based on second-generation Maxwell, the full realization of the Maxwell architecture. Today NVIDIA introduced the new GM204 GPU, based on the Maxwell architecture.
0 kommentar(er)
