AMD Radeon RX 540 vs NVIDIA GeForce 930M vs NVIDIA GeForce 940M

AMD Radeon RX 540

The AMD Radeon RX 540 is mobile mid-range graphics card for laptops based on the Polaris 12 chip (most likely). It is manufactured in an improved 14 nm FinFET process at Globalfoundries. The performance should be between the Radeon Pro 450 and 455 in the MacBook Pro 2016 range that is also based on the Polaris architecture. AMD specifies the RX 450 at 1.2 TFLOPS (Pro 450 1 TFLOP, Pro 455 1.3 TFLOPs). Compared to Nvidia graphics cards, the gaming performance should be between the GeForce GTX 950M and GTX 960M.

The features of the Radeon RX 540 are identical to the faster RX 460 and all other Polaris chips. See more details on the Polaris architecture here.

The power envelope of the faster Radeon Pro 460 is rated at 35 Watt according to the AMD blog post. Due to the slower specs, the Radeon RX 540 use slightly less.

NVIDIA GeForce 930M

The NVIDIA GeForce 930M (sometimes also called Nvidia GeForce GT 930M) is a (lower) mid-range, DirectX 11-compatible graphics card for laptops unveiled in March 2015. It is based on the last years GeForce 840M. In addition to the "normal" 25 Watt 930M, there is also a low power variant with a TDP of 12 Watt and support for DDR3 and GDDR5. The DDR3 variant should be approximately 10% slower than the 25 Watt version. The performance of the GDDR5 version is still unknown. The shader count for these low power 930M are also unknown. As the LP version is clocked only at 457 MHz + Boost it may feature more shaders (or a high Boost).

Update: The N16S-LP variant (5-12 Watt TDP, Low Power version?) will be available with GDDR5 starting in the first quarter of 2016. Later in 2016, the successor named GeForce 930MX was released that was available with GDDR5.

Architecture

Compared to Kepler, Maxwell has been optimized in several details to increase power efficiency. Smaller Streaming Multiprocessors (SMM) with only 128 ALUs (Kepler: 192) and an optimized scheduler should lead to better utilization of the shaders. Nvidia promises that a Maxwell SMM with 128 ALUs can offer 90 percent of the performance of a Kepler SMX with 192 ALUs. The 930M should feature the full GM108 with 3 SMMs (384 shader cores, 24 TMUs, and 8 ROPs due to the 64-bit interface). 

Another optimization is the massively enlarged L2 cache. The larger size can process some of the memory traffic to allow for a relatively narrow memory interface without significantly reducing performance.

Similar to GM107, the GM108 supports DirectX 12 with Feature Level 11_0 only.

Performance

The performance should be a bit below an average GeForce 840M due to the slower core clock. This means that demanding games like Evolve are only playable in lowest settings. Less demanding games like F1 2014 or Fifa 15 on the other hand should run in highest settings. See gaming benchmarks below for more details.

Features

GM108 integrates the sixth generation of the PureVideo HD video engine (VP6), offering a better decoding performance for H.264 and MPEG-2 videos. Of course, VP6 supports all features of previous generations (4K support, PIP, video encoding via NVENC API). Unfortunately, HDMI 2.0 is still not supported.

Power Consumption

The power consumption of the GeForce 930M should be about 33 Watts or less. Therefore, the 930M is best suited for laptops 13 inches in size or larger. The 900M series also supports Optimus to automatically switch between an integrated graphics card and the Nvidia GPU.

NVIDIA GeForce 940M

The NVIDIA GeForce 940M is a mid-range DirectX 11-compatible graphics card for laptops unveiled in March 2015. It is based on Nvidia's Maxwell architecture (GM108 chip) and manufactured in 28 nm. The 940M offers 384 shader units as well as 2 GB of DDR3 memory (64 bit, 2000 MHz effective).

Compared to the previous and technically very similar GeForce 840M, the GeForce 940M is clocked just slightly higher.

Architecture

Compared to Kepler, Maxwell has been optimized in several details to increase power efficiency. Smaller Streaming Multiprocessors (SMM) with only 128 ALUs (Kepler: 192) and an optimized scheduler should lead to better utilization of the shaders. Nvidia promises that a Maxwell SMM with 128 ALUs can offer 90 percent of the performance of a Kepler SMX with 192 ALUs. GM108 features 3 SMMs and thus 384 shader cores, 24 TMUs and 8 ROPs (64-bit interface).

Another optimization is the massively enlarged L2 cache. The larger size can process some of the memory traffic to allow for a relatively narrow memory interface without significantly reducing performance.

Similar to Fermi and Kepler, the GM107/GM108 support DirectX 12 with feature level 11_0 only.

Performance

Due to its just 5 percent higher core clock, the GeForce 940M is only marginally faster than the previous GeForce 840M and similar to the older GeForce GT 750M (DDR3 version). Many games of 2014/2015 can be played fluently in WXGA resolution (1366 x 768) and medium detail settings. However, very demanding games such as Assassin's Creed Unity will require lower resolutions and/or details.

Features

GM108 integrates the sixth generation of the PureVideo HD video engine (VP6), offering a better decoding performance for H.264 and MPEG-2 videos. Of course, VP6 supports all features of previous generations (4K support, PIP, video encoding via NVENC API). Unfortunately, HDMI 2.0 is still not supported.

Power Consumption

The power consumption of the GeForce 940M should be about 30 Watts or lower. Therefore, the GPU is best suited for laptops 13 - 14 inches in size and above. The 900M series also supports Optimus to automatically switch between an integrated graphics card and the Nvidia GPU.