NVIDIA GeForce 940M vs NVIDIA GeForce GTX 550 Ti Comparison

The Verdict

The data presents a clear split: the NVIDIA GeForce 940M wins the only recorded head-to-head benchmark, the Geekbench OpenCL test, with a score of 6018 against the GTX 550 Ti's 5731. That is a 4.8% advantage for the 940M, a meaningful but not overwhelming lead. The 940M also shows a Vulkan score of 4549, a capability the GTX 550 Ti cannot offer at all, as it has no recorded Vulkan result.

However, the GTX 550 Ti is not without its own arguments. Its single OpenCL score of 5731 places it in the 33rd percentile of all GPUs, while the 940M's average benchmark score of 5284 sits in the 31st percentile. The 940M's average is dragged down by its two benchmark results, but its OpenCL peak is higher. The GTX 550 Ti also has a higher transistor density advantage in reverse: it packs 1,170 million transistors on a 238 mm² die, while the 940M fits 1,870 million transistors on a much smaller 148 mm² die. The 940M is the more modern design, but the GTX 550 Ti remains competitive in raw compute.

For buyers, the 940M is the safer pick for modern workloads that leverage Vulkan and higher FP32 throughput. The GTX 550 Ti, with its older Fermi architecture and higher 116 W TDP, is a desktop card from an earlier era. The 940M's lower 75 W TDP and MXM form factor make it a mobile-oriented part, while the GTX 550 Ti is a dual-slot desktop card requiring a 300 W power supply and a 6-pin connector. The data does not support a universal winner, but it does suggest the 940M is the more versatile modern option.

Architecture Differences

The two GPUs come from different architectural generations. The GTX 550 Ti uses the GF116 chip, built on Fermi 2.0 architecture, fabricated on a 40 nm process at TSMC. The 940M uses the GM107 chip, built on Maxwell architecture, also at TSMC but on a 28 nm process. This process shrink is significant: the 940M fits 1,870 million transistors into a 148 mm² die, while the GTX 550 Ti fits only 1,170 million into a larger 238 mm² die. The resulting transistor density tells the story: the 940M achieves 12.6M transistors per mm², compared to the GTX 550 Ti's 4.9M per mm².

The 940M's Maxwell architecture brings a higher transistor count and a smaller die, which explains its better FP32 performance. The GTX 550 Ti has 192 shading units, 32 texture mapping units, and 24 ROPs. The 940M has 512 shading units, 32 TMUs, and 16 ROPs. Despite having fewer ROPs, the 940M achieves a higher pixel rate of 17.57 GPixel/s versus the GTX 550 Ti's 7.2 GPixel/s. Its texture rate is also higher: 35.14 GTexel/s versus 28.8 GTexel/s. FP32 compute is dramatically higher on the 940M: 1,124.4 GFLOPS versus 691.2 GFLOPS.

Memory configurations differ substantially. The GTX 550 Ti uses 1024 MB of GDDR5 on a 192-bit bus, delivering 98.50 GB/s of bandwidth. The 940M uses 2 GB of DDR3 on a 64-bit bus, delivering only 14.40 GB/s. That is a massive bandwidth deficit for the 940M, yet its OpenCL score is still higher, suggesting that compute efficiency, not bandwidth, drives the result. The GTX 550 Ti's memory clock is listed at 1026 MHz (4.1 Gbps effective), while the 940M runs at 900 MHz (1800 Mbps effective).

The 940M supports Vulkan 1.4, while the GTX 550 Ti has no Vulkan support recorded. Both support DirectX 12 (11_0) and OpenGL 4.6. The GTX 550 Ti uses PCIe 2.0 x16, while the 940M uses MXM-B (3.0), reflecting its laptop-oriented design. The 940M's display outputs are listed as "Portable Device Dependent," while the GTX 550 Ti offers 2x DVI and 1x mini-HDMI 1.3a. The GTX 550 Ti is a dual-slot card, 210 mm long, with a 1x 6-pin power connector and a 300 W suggested PSU. The 940M is an MXM module with no power connectors and a 75 W TDP.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce 940M scores 6018 in Geekbench OpenCL, which is 4.8% higher than the GTX 550 Ti's 5731.

Q: Does the GTX 550 Ti support Vulkan?

A: No Vulkan support is recorded for the GTX 550 Ti. The 940M, in contrast, has a Geekbench Vulkan score of 4549 and supports Vulkan 1.4.

Q: How do their memory bandwidths compare?

A: The GTX 550 Ti offers 98.50 GB/s from its GDDR5 memory on a 192-bit bus, while the 940M offers only 14.40 GB/s from DDR3 on a 64-bit bus.

Q: Which GPU has more shading units?

A: The 940M has 512 shading units, while the GTX 550 Ti has 192. The 940M also delivers higher FP32 compute at 1,124.4 GFLOPS versus 691.2 GFLOPS.

Q: What are the power requirements for each?

A: The GTX 550 Ti has a 116 W TDP, requires a 300 W suggested PSU, and uses a 1x 6-pin power connector. The 940M has a 75 W TDP and uses no power connectors, as it is an MXM module.

Q: Which GPU is in a higher percentile of all GPUs based on the database?

A: The GTX 550 Ti sits at the 33rd percentile, while the 940M sits at the 31st percentile based on its average benchmark score of 5284.

Specification Differences

The two cards differ in nearly every physical and technical specification. The GTX 550 Ti uses the GF116 chip on Fermi 2.0 at 40 nm, while the 940M uses GM107 on Maxwell at 28 nm. The GTX 550 Ti has 1,170 million transistors on a 238 mm² die, while the 940M has 1,870 million on 148 mm². Transistor density is 4.9M per mm² for the GTX 550 Ti and 12.6M for the 940M.

Memory differs completely: the GTX 550 Ti has 1024 MB GDDR5 on a 192-bit bus with 98.50 GB/s bandwidth, while the 940M has 2 GB DDR3 on a 64-bit bus with 14.40 GB/s. Shading units are 192 versus 512, TMUs are 32 for both, and ROPs are 24 versus 16. Pixel rate is 7.2 GPixel/s for the GTX 550 Ti and 17.57 for the 940M. Texture rate is 28.8 GTexel/s versus 35.14. FP32 is 691.2 GFLOPS versus 1,124.4. The GTX 550 Ti has a 116 W TDP, while the 940M has 75 W. The GTX 550 Ti is a dual-slot card with a 1x 6-pin connector and a 300 W PSU suggestion, while the 940M is an MXM module with no connectors. The GTX 550 Ti uses PCIe 2.0 x16, while the 940M uses MXM-B (3.0). Display outputs are 2x DVI and 1x mini-HDMI for the GTX 550 Ti, while the 940M's are portable-device dependent. The GTX 550 Ti supports DirectX 12 (11_0) and OpenGL 4.6, and the 940M adds Vulkan 1.4. The GTX 550 Ti has a launch MSRP of 149 USD, while the 940M has no recorded launch MSRP.

Head-to-Head Benchmarks

The database records one head-to-head benchmark: Geekbench OpenCL. In that test, the 940M wins with a score of 6018, and the GTX 550 Ti scores 5731, a delta of 4.8% in favor of the 940M. The 940M's OpenCL score is also its peak performance in the database. The GTX 550 Ti's 5731 is its only recorded score, so its average benchmark score is also 5731.

The 940M's wins are not limited to OpenCL. It also has a Geekbench Vulkan score of 4549, a benchmark category where the GTX 550 Ti has no recorded result. This gives the 940M a second clear victory in a modern API. The GTX 550 Ti, however, holds a percentile advantage: 33rd versus 31st, based on the 940M's average score of 5284 across two tests. The GTX 550 Ti's nearest rivals include the GTX 670MX (5721, delta 0.2%), the Intel Iris Pro Graphics P6300 (5712, delta 0.3%), the AMD Radeon HD 8790M (5691, delta 0.7%), and the AMD Radeon R7 M465 (5841, delta -1.9%). The 940M's rivals include the GTX 980M (5308, delta -0.4%), the GeForce 930A (5317, delta -0.6%), the GeForce 840M (5322, delta -0.7%), and the GTX 760M (5236, delta 0.9%).

The single OpenCL win is decisive but narrow. A 4.8% margin is not a blowout, but the 940M's Vulkan result adds weight to its case. The GTX 550 Ti's higher percentile percentile is a minor point, but it does indicate that its single score is competitive with many GPUs in the 33rd percentile range.

Where Each One Wins

The 940M wins in compute-heavy scenarios that favor modern architectures. Its FP32 throughput of 1,124.4 GFLOPS is 62.6% higher than the GTX 550 Ti's 691.2 GFLOPS. Its pixel rate of 17.57 GPixel/s is more than double the GTX 550 Ti's 7.2 GPixel/s, and its texture rate of 35.14 GTexel/s beats 28.8 GTexel/s. The 940M also has Vulkan support, which is absent on the GTX 550 Ti. For any workload that uses modern APIs or relies on shader compute, the 940M is the stronger GPU.

The GTX 550 Ti wins in memory bandwidth. Its 98.50 GB/s is nearly seven times the 940M's 14.40 GB/s. This is a huge advantage for bandwidth-sensitive tasks like high-resolution texturing or certain rendering workloads. The GTX 550 Ti also has a higher ROP count (24 versus 16), which historically helps with fill-rate-bound operations, although its pixel rate is lower. The GTX 550 Ti sits in a higher percentile (33rd) than the 940M (31st), which suggests that its single score is more representative of a broader range of GPUs.

For desktop users with existing power supplies and PCIe slots, the GTX 550 Ti is a drop-in card with a 300 W PSU requirement and a 6-pin connector. For laptop users, the 940M is an MXM module with no power connector and a 75 W TDP. The 940M's 2 GB memory capacity doubles the GTX 550 Ti's 1 GB, though the GTX 550 Ti's GDDR5 is faster. The data suggests a split: the 940M for modern compute and API support, the GTX 550 Ti for bandwidth-heavy desktop workloads. Neither card dominates the other, but the 940M's OpenCL and Vulkan wins give it the edge in the recorded benchmarks.