Maxwell (microarchitecture)

From Wikipedia, the free encyclopedia
Jump to: navigation, search
Nvidia Maxwell
Predecessor Kepler
Successor Pascal

Maxwell is the codename for a GPU microarchitecture developed by Nvidia as the successor to the Kepler microarchitecture. The Kepler architecture was used in GeForce 700 series GPUs manufactured in 28 nm and continued in the GeForce 800M series manufactured in 28 nm[1] initially, moving to a smaller node in 2015.

The very first Maxwell-based product to hit the market were the GeForce GTX 750 and the GeForce GTX 750 Ti. Both were released on February 18, 2014, both with the chip code number GM107, easily distinguishable from the Kepler Chips with the code numbers GK1xx.

Maxwell introduced an all-new design for the Streaming Multiprocessor (SM) that dramatically improves power efficiency.[2]

Maxwell introduced the sixth generation PureVideo HD and CUDA Compute Capability 5.2.

First generation Maxwell (GM10x)[edit]

First generation Maxwell GM107/GM108 provides few consumer-facing additional features; Nvidia instead focused on power efficiency. Nvidia increased the amount of L2 cache from 256 KiB on GK107 to 2 MiB on GM107, reducing the memory bandwidth needed. Accordingly, Nvidia cut the memory bus from 192 bit on GK106 to 128 bit on GM107, further saving power.[3] Nvidia also changed the streaming multiprocessor design from that of Kepler (SMX), naming it SMM. The layout of SMM units is partitioned so that each of the four warp schedulers controls isolated FP32 CUDA cores, load/store units and special function units, unlike Kepler, where the warp schedulers share the resources. Texture units and FP64 CUDA cores are still shared.[3] SMM allows for a finer-grain allocation of resources than SMX, saving power when the workload isn't optimal for shared resources. Nvidia claims a 128 CUDA core SMM has 90% of the performance of a 192 CUDA core SMX.[3]

GM107 supports CUDA Compute Capability 5.0 compared to 3.5 on GK110/GK208 GPUs and 3.0 on GK10x GPUs. Dynamic Parallelism and HyperQ, two features in GK110/GK208 GPUs, are also supported across the entire Maxwell product line.

Maxwell provides native shared memory atomic operations for 32-bit integers and native shared memory 32-bit and 64-bit compare-and-swap (CAS), which can be used to implement other atomic functions.


Main article: Nvidia NVENC

Maxwell-based GPUs also contain the NVENC SIP block introduced with Kepler. Nvidia's video encoder, NVENC, is 1.5 to 2 times faster than on Kepler-based GPUs meaning it can encode video at 6 to 8 times playback speed.[3]


Main article: Nvidia PureVideo

Nvidia also claims an 8 to 10 times performance increase in PureVideo Feature Set E video decoding due to the video decoder cache paired with increases in memory efficiency. However, H.265 is not supported for full hardware decoding, relying on a mix of hardware and software decoding.[3] When decoding video, a new low power state "GC5" is used on Maxwell GPUs to conserve power.[3]

Second generation Maxwell (GM20x)[edit]

Second generation Maxwell introduced several new technologies: Dynamic Super Resolution,[4] Third Generation Delta Color Compression,[5] Multi-Pixel Programming Sampling,[6] Nvidia VXGI (Real-Time-Voxel-Global Illumination),[7] VR Direct,[8][9][10] Multi-Projection Acceleration,[5] and Multi-Frame Sampled Anti-Aliasing(MFAA)[11] however support for CSAA was removed.[12] HDMI 2.0 support was also added.[13][14]

GM204 supports CUDA Compute Capability 5.2 compared to 5.0 on GM107/GM108 GPUs, 3.5 on GK110/GK208 GPUs and 3.0 on GK10x GPUs.[5][15]


After Maxwell, the next architecture will be codenamed Pascal.[16] Nvidia has announced that the Pascal GPU will feature stacked DRAM, Unified Memory, and NVLink.[16]

See also[edit]


  1. ^
  2. ^ "5 Things You Should Know About the New Maxwell GPU Architecture". 2014-02-21. 
  3. ^ a b c d e f Smith, Ryan; T S, Ganesh (18 February 2014). "The NVIDIA GeForce GTX 750 Ti and GTX 750 Review: Maxwell Makes Its Move". AnandTech. Archived from the original on 18 February 2014. Retrieved 18 February 2014. 
  4. ^
  5. ^ a b c
  6. ^
  7. ^
  8. ^
  9. ^
  10. ^
  11. ^
  12. ^
  13. ^
  14. ^
  15. ^
  16. ^ a b