AMD Radeon Pro 555X vs NVIDIA GeForce GTX 960A Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark recorded in the database for both parts is Geekbench OpenCL. In that test, the AMD Radeon Pro 555X scores 12,628 points against the NVIDIA GeForce GTX 960A's 11,998 points. That is a 5.3% advantage for the AMD part, a meaningful margin in raw compute workloads that lean on OpenCL execution.

The AMD Radeon Pro 555X also has additional benchmark entries that the NVIDIA part lacks: Geekbench Metal at 14,479 and Geekbench Vulkan at 12,855. These do not form a head-to-head comparison because the GTX 960A has no recorded score for either test, but they establish the AMD card's broader API coverage in the database. The GeForce GTX 960A is only tested under OpenCL, so its average benchmark score of 11,998 exactly matches that single result.

When placed against the wider GPU field, the AMD part sits at the 54th percentile of all GPUs, while the NVIDIA part sits at the 51st percentile. The AMD card's average benchmark score across all tests is 13,321. Its nearest rivals in the database are the NVIDIA GeForce GTX 480 at 13,300 (0.2% ahead), the AMD FirePro M6100 at 13,354 (0.2% behind), the AMD Radeon RX 5500M at 13,356 (0.3% behind), and the AMD Radeon HD 8950M at 13,376 (0.4% behind). The Radeon Pro 555X is effectively in a tight cluster with those parts, with less than half a percent separating it from any of them.

The NVIDIA GeForce GTX 960A's average score of 11,998 puts its nearest rivals at the NVIDIA GeForce GTX 1080 with 11,960 (0.3% ahead of the 960A), the AMD Radeon RX 6500 XT at 11,842 (1.3% behind), the NVIDIA GeForce GTX 1660 at 11,680 (2.7% behind), and the AMD Radeon RX 7800 XT at 11,627 (3.2% behind). The GTX 960A is therefore at the top of its immediate cluster, leading the next-closest competitor by a small margin.

The head-to-head data shows a single winner out of the one shared test: the AMD Radeon Pro 555X wins that test, giving it 1 win total in this comparison, while the NVIDIA GeForce GTX 960A records no wins in any shared benchmark.

Where Each One Wins

The AMD Radeon Pro 555X wins the only directly comparable workload, Geekbench OpenCL, by 5.3%. That makes it the stronger choice for OpenCL compute tasks in this pairing. Its additional Metal score of 14,479 and Vulkan score of 12,855 further suggest it is the more versatile part across multiple API environments, though no direct NVIDIA comparison exists for those tests.

The NVIDIA GeForce GTX 960A does not win any recorded benchmark against the AMD part. However, its position relative to its own nearest rivals is slightly stronger: it leads the GTX 1080 by 0.3% and the RX 6500 XT by 1.3%, whereas the AMD part sits almost exactly level with its nearest competitors. This indicates the GTX 960A is a stronger performer within its own reference class, even if it loses the direct comparison.

For use cases where OpenCL is the primary workload, the data points to the AMD part. For scenarios where the GPU is constrained by the mobile or MXM form factor, the GTX 960A still delivers competitive OpenCL throughput, sitting within 5.3% of the AMD card despite its older architecture and smaller memory allocation.

Architecture Differences

The AMD Radeon Pro 555X is built on the Polaris 21 chip using GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. It integrates 3,000 million transistors on a 123 mm² die, yielding a transistor density of 24.4 million per mm². The NVIDIA GeForce GTX 960A uses the GM107 chip with Maxwell architecture, produced on a 28 nm process at TSMC. It contains 1,870 million transistors across a 148 mm² die, for a density of 12.6 million per mm².

The AMD part has 768 shading units, 48 texture mapping units, and 16 ROPs. The NVIDIA part has 640 shading units, 40 texture mapping units, and 16 ROPs. The AMD card therefore has more shaders and more TMUs, while ROP counts match.

Clock behavior differs notably. The NVIDIA card has recorded base and boost clocks of 1097 MHz and 1176 MHz respectively. The AMD card has no base or boost clock listed in the database, only a memory clock of 1470 MHz with 5.9 Gbps effective data rate. The NVIDIA memory clock is 1253 MHz with 5 Gbps effective.

Memory configurations diverge sharply. The AMD Radeon Pro 555X has 4 GB of GDDR5 on a 128 bit bus, delivering 94.08 GB/s of bandwidth. The NVIDIA GeForce GTX 960A has 2 GB of GDDR5 on a 128 bit bus, with 80.19 GB/s of bandwidth. The AMD card doubles capacity and provides 17.3% more bandwidth.

Pixel and texture rates follow the clock and unit differences. The AMD card achieves 14.51 GPixel/s and 43.54 GTexel/s. The NVIDIA card achieves 18.82 GPixel/s and 47.04 GTexel/s. Despite fewer ROPs, the NVIDIA part's higher clocks produce a faster pixel fill rate. Its higher TMU count combined with high clocks also gives it a texture rate advantage.

Compute throughput is close. The AMD card delivers 1,393.2 GFLOPS of FP32, and the same figure for FP16 at a 1:1 ratio. The NVIDIA card delivers 1.505 TFLOPS of FP32, which is approximately 8% higher, but it has no recorded FP16 capability.

Both cards are rated at 75 W TDP and require no power connectors. The AMD part is an integrated GPU (IGP) form factor, while the NVIDIA part is an MXM module. Both use PCIe-class interfaces: the AMD card uses PCIe 3.0 x8, the NVIDIA card uses MXM-B (3.0).

API support differs as well. The AMD card lists DirectX 12 (12_0, meaning it is a DirectX 12_0 part), OpenGL 4.6, and Vulkan 1.3. The NVIDIA card lists DirectX 12 (11_0, meaning it is a DirectX 11_0 part), OpenGL 4.6, and Vulkan 1.4.

Both cards are marked end-of-life in production status. The AMD part was released on July 15, 2018, while the NVIDIA card was released on March 12, 2015. The NVIDIA card's predecessor is listed as the GeForce 800A; the AMD card has no predecessor or successor listed.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon Pro 555X has an average benchmark score of 13,321 across all tests. The NVIDIA GeForce GTX 960A has an average of 11,998. The AMD part leads by 123 points, or 5.3% in the shared OpenCL test.

Q: How much memory does each card have?

A: The AMD Radeon Pro 555X has 4 GB of GDDR5 on a 128 bit bus. The NVIDIA GeForce GTX 960A has 2 GB of GDDR5 on a 128 bit bus.

Q: What is the transistor count difference between the two chips?

A: The AMD Polaris 21 chip contains 3,000 million transistors. The NVIDIA GM107 contains 1,870 million transistors. The AMD die size is 123 mm², the NVIDIA die is 148 mm².

Q: Which card supports Vulkan 1.4?

A: The NVIDIA GeForce GTX 960A lists Vulkan 1.4. The AMD Radeon Pro 555X lists Vulkan 1.3.

Q: What are the TDP ratings?

A: Both cards are rated at 75 W TDP and require no power connectors.

Q: Which card has a recorded base clock?

A: The NVIDIA GeForce GTX 960A has a base clock of 1097 MHz and a boost clock of 1176 MHz. The AMD Radeon Pro 555X has no base or boost clock recorded in the database, only a memory clock of 1470 MHz (5.9 Gbps effective).

Specification Differences

• Process Node: AMD Radeon Pro 555X is 14 nm (GlobalFoundries); NVIDIA GeForce GTX 960A is 28 nm (TSMC).
• Transistors: 3,000 million vs 1,870 million.
• Die Size: 123 mm² vs 148 mm².
• Transistor Density: 24.4M / mm² vs 12.6M / mm².
• Architecture: GCN 4.0 vs Maxwell.
• Chip: Polaris 21 vs GM107.
• Generation: Radeon Pro Mac (500X Series) vs GeForce 900A.
• Base Clock: Not listed vs 1097 MHz.
• Boost Clock: Not listed vs 1176 MHz.
• Memory Clock: 1470 MHz (5.9 Gbps effective) vs 1253 MHz (5 Gbps effective).
• Memory Size: 4 GB vs 2 GB.
• Memory Type: Both GDDR5.
• Memory Bus Width: Both 128 bit.
• Memory Bandwidth: 94.08 GB/s vs 80.19 GB/s.
• Shading Units: 768 vs 640.
• TMUs: 48 vs 40.
• ROPs: 16 vs 16.
• Pixel Rate: 14.51 GPixel/s vs 18.82 GPixel/s.
• Texture Rate: 43.54 GTexel/s vs 47.04 GTexel/s.
• FP32: 1,393.2 GFLOPS vs 1.505 TFLOPS.
• FP16: 1,393.2 GFLOPS (1:1) vs not listed.
• TDP: Both 75 W.
• Slot Width: IGP vs MXM Module.
• Bus Interface: PCIe 3.0 x8 vs MXM-B (3.0).
• DirectX: 12 (12_0) vs 12 (11_0).
• Vulkan: 1.3 vs 1.4.
• Release Date: 2018-07-15 vs 2015-03-12.
• Predecessor: Not listed vs GeForce 800A.
• Percentile vs All GPUs: 54 vs 51.
• Average Benchmark Score: 13,321 vs 11,998.
• Geekbench OpenCL Score: 12,628 vs 11,998.
• Additional Benchmark Scores: Geekbench Metal 14,479, Geekbench Vulkan 12,855 (AMD only); none for NVIDIA.