AMD Radeon R9 M360 vs NVIDIA GeForce GTX 650 Ti Boost Comparison

The AMD Radeon R9 M360 and NVIDIA GeForce GTX 650 Ti Boost are both end-of-life products from different eras, with the former being a mobile-oriented part from 2015 and the latter a desktop card from 2013. Despite the age gap, benchmark data places them in a similar performance tier, with the GTX 650 Ti Boost showing a clear edge in compute workloads. This analysis compares their head-to-head results, architectural choices, and the specific scenarios where each GPU holds an advantage.

Head-to-Head Benchmarks

The data from the two shared benchmark tests is unambiguous: the NVIDIA GeForce GTX 650 Ti Boost wins both matchups decisively. In the Geekbench OpenCL test, the GTX 650 Ti Boost scores 9302, while the AMD Radeon R9 M360 scores 8211. This represents an 11.7% advantage for NVIDIA, a substantial margin that indicates a significant gap in raw compute throughput. The Vulkan test shows an even wider divide, with the GTX 650 Ti Boost scoring 10041 against the R9 M360's 8047. That is a 19.9% delta, nearly a fifth faster than the AMD part in this API.

These results paint a clear picture of performance hierarchy. The R9 M360's average benchmark score sits at 8129, while the GTX 650 Ti Boost's average is 8067. Interestingly, the AMD card actually has a slightly higher average score despite losing both head-to-head matchups, which highlights how different test suites can skew results. The R9 M360's nearest rival is the NVIDIA GeForce GTX 950M, which scores 8135, a delta of just -0.1%, meaning the AMD card is effectively tied with that mobile NVIDIA part. Meanwhile, the GTX 650 Ti Boost's closest competitor is the NVIDIA GRID K2, scoring 8080, a -0.2% delta, again showing a near-identical performance level.

The Vulkan result is particularly telling for the NVIDIA card. A 19.9% lead over the R9 M360 suggests that the GTX 650 Ti Boost's architecture handles modern API overhead more efficiently, or that its higher raw specifications simply overwhelm the AMD part. The OpenCL gap, while smaller, still gives NVIDIA a comfortable 11.7% win. In aggregate, the GTX 650 Ti Boost demonstrates superior compute performance across the board, with both GPUs sitting at the 42nd percentile of all GPUs, indicating they are firmly mid-range performers by today's standards.

Architecture Differences

The architectural divide between these two GPUs is stark. The AMD Radeon R9 M360 is built on the "Tropo" chip using GCN 1.0 architecture, manufactured on a 28 nm process at TSMC. It packs 1,500 million transistors into a 123 mm² die, resulting in a transistor density of 12.2M per mm². In contrast, the NVIDIA GeForce GTX 650 Ti Boost uses the GK106 chip with Kepler architecture, also on a 28 nm TSMC process, but with a much larger 221 mm² die containing 2,540 million transistors, giving a density of 11.5M per mm².

The core configurations differ significantly. The R9 M360 has 512 shading units, 32 texture mapping units (TMUs), and 16 raster operation units (ROPs). The GTX 650 Ti Boost counters with 768 shading units, 64 TMUs, and 24 ROPs. This means NVIDIA's card has 50% more shading units, exactly double the TMUs, and 50% more ROPs. These are not small differences; they translate directly into the texture fillrate and pixel throughput numbers. The R9 M360 achieves 29.60 GTexel/s and 14.80 GPixel/s, while the GTX 650 Ti Boost hits 66.05 GTexel/s and 16.51 GPixel/s. The texture rate gap is particularly large, with NVIDIA delivering over twice the texel throughput.

Clock speeds also favor NVIDIA. The R9 M360 runs at a 900 MHz base and 925 MHz boost, while the GTX 650 Ti Boost runs at 980 MHz base and 1032 MHz boost. Combined with the higher core counts, this yields a significant FP32 compute advantage: the R9 M360 delivers 947.2 GFLOPS, whereas the GTX 650 Ti Boost delivers 1.585 TFLOPS, a 67% higher figure. Neither card supports FP16, RT cores, or tensor cores, so those fields are null for both.

The memory subsystems are also divergent. The R9 M360 features 4 GB of GDDR5 on a 128-bit bus, yielding 72.00 GB/s of bandwidth. The GTX 650 Ti Boost has 2 GB of GDDR5 on a 192-bit bus, producing 144.2 GB/s of bandwidth. The NVIDIA card has exactly double the memory bandwidth, which is crucial for high-resolution textures and compute workloads. The AMD card compensates with double the memory capacity, which can be beneficial for large datasets that fit within 4 GB but exceed 2 GB.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R9 M360 has an average benchmark score of 8129, while the NVIDIA GeForce GTX 650 Ti Boost has an average of 8067. Despite this, the GTX 650 Ti Boost wins both head-to-head benchmark tests.

Q: What is the largest performance gap between the two cards?

A: The largest gap is in the Geekbench Vulkan test, where the GTX 650 Ti Boost scores 10041 versus the R9 M360's 8047, a 19.9% difference. The OpenCL test shows a smaller but still significant 11.7% gap.

Q: How do their memory bandwidth figures compare?

A: The GTX 650 Ti Boost offers 144.2 GB/s of bandwidth, which is exactly double the R9 M360's 72.00 GB/s. However, the R9 M360 has 4 GB of memory, twice the GTX 650 Ti Boost's 2 GB.

Q: Are these GPUs comparable in transistor density?

A: Yes, they are very close. The R9 M360 has a transistor density of 12.2M per mm², while the GTX 650 Ti Boost has 11.5M per mm². Both are built on a 28 nm TSMC process.

Q: What is the DirectX support difference?

A: The R9 M360 supports DirectX 12 (11_1), while the GTX 650 Ti Boost supports DirectX 12 (11_0). Both support OpenGL 4.6, but the NVIDIA card has a slightly newer Vulkan version (1.2.175 vs 1.2.170).

Q: How do their nearest rivals compare to the R9 M360?

A: The R9 M360's closest rival is the NVIDIA GeForce GTX 950M, which scores 8135, just 0.1% higher. It also sits near the NVIDIA GeForce 945M (8099, 0.4% lower) and the NVIDIA GeForce GTX 980 (8167, 0.5% higher).

Specification Differences

The two GPUs differ across nearly every major specification category. The process node is identical (28 nm, TSMC), but the die sizes and transistor counts diverge sharply: the R9 M360 uses a 123 mm² die with 1,500 million transistors, while the GTX 650 Ti Boost uses a 221 mm² die with 2,540 million transistors. This leads to different transistor densities, 12.2M vs 11.5M per mm².

Clock speeds favor NVIDIA, with the GTX 650 Ti Boost running at 980 MHz base and 1032 MHz boost, versus the R9 M360's 900 MHz base and 925 MHz boost. The memory clocks also differ, with the R9 M360 at 1125 MHz (4.5 Gbps effective) and the GTX 650 Ti Boost at 1502 MHz (6 Gbps effective). In terms of memory, the AMD card has 4 GB on a 128-bit bus, while the NVIDIA card has 2 GB on a 192-bit bus, resulting in bandwidths of 72.00 GB/s and 144.2 GB/s, respectively.

The compute configurations are heavily in NVIDIA's favor: the R9 M360 has 512 shading units, 32 TMUs, and 16 ROPs, while the GTX 650 Ti Boost has 768 shading units, 64 TMUs, and 24 ROPs. This yields a pixel rate of 14.80 GPixel/s for AMD versus 16.51 GPixel/s for NVIDIA, and a texture rate of 29.60 GTexel/s versus 66.05 GTexel/s. The FP32 performance is 947.2 GFLOPS for AMD versus 1.585 TFLOPS for NVIDIA.

Power and physical specifications only exist for the NVIDIA card, which has a 134 W TDP, a dual-slot width, a 1x 6-pin power connector, a 300 W suggested PSU, and a length of 241 mm (9.5 inches). The R9 M360 has no listed TDP, slot width, power connectors, or dimensions. Display outputs also differ, with the GTX 650 Ti Boost offering 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the R9 M360 has none listed. The NVIDIA card also has a launch MSRP of 169 USD, though the AMD card has no launch price listed.

The Verdict

The data is decisive: the NVIDIA GeForce GTX 650 Ti Boost is the superior performer in compute benchmarks. It wins both head-to-head tests, with an 11.7% lead in OpenCL and a 19.9% lead in Vulkan. Its hardware specifications are uniformly stronger, from shading units (768 vs 512) to TMUs (64 vs 32) to ROPs (24 vs 16), and it delivers more than double the texture fillrate and 67% higher FP32 compute. The GTX 650 Ti Boost also has twice the memory bandwidth, which gives it a substantial advantage in bandwidth-bound workloads.

However, the R9 M360 is not without merit. It offers 4 GB of memory, which is double the NVIDIA card's 2 GB, and it has a slightly higher average benchmark score (8129 vs 8067). Its smaller die size (123 mm² vs 221 mm²) and lower transistor count (1,500 million vs 2,540 million) suggest it is a more power-efficient design, though power data is only available for the NVIDIA card. The R9 M360 also has a newer DirectX feature level (12 (11_1) vs 12 (11_0)), which could matter for specific modern titles.

For users prioritizing raw compute performance, the GTX 650 Ti Boost is the clear choice. Its benchmark wins are consistent and significant, and its architecture provides superior throughput across the board. The R9 M360's only advantage is memory capacity, which matters only if a workload requires more than 2 GB of VRAM. Given that both cards are end-of-life and sit at the 42nd percentile of all GPUs, neither is a modern powerhouse, but the data shows NVIDIA's offering as the stronger performer.

Where Each One Wins

The NVIDIA GeForce GTX 650 Ti Boost wins in every measured benchmark category. In OpenCL, it scores 9302 against the R9 M360's 8211, a win that reflects its higher shading unit count and memory bandwidth. The Vulkan test is even more lopsided, with the GTX 650 Ti Boost scoring 10041 versus 8047, a 19.9% advantage that suggests Kepler handles this API particularly well. The NVIDIA card also wins on texture throughput (66.05 GTexel/s vs 29.60 GTexel/s), pixel rate (16.51 GPixel/s vs 14.80 GPixel/s), and raw FP32 compute (1.585 TFLOPS vs 947.2 GFLOPS). Its 144.2 GB/s memory bandwidth is exactly double the AMD card's 72.00 GB/s, giving it a distinct edge in any memory-intensive scenario.

The AMD Radeon R9 M360 wins only on memory capacity, offering 4 GB versus the GTX 650 Ti Boost's 2 GB. This could be an advantage in scenarios where texture sets or datasets exceed 2 GB, such as certain modded games or compute workloads with large buffers. The R9 M360 also has a slightly higher average benchmark score (8129 vs 8067), though this is marginal and contradicted by the head-to-head results. Its smaller die and transistor count hint at better efficiency, but without TDP data for the AMD card, this remains speculative. The R9 M360's DirectX 12 (11_1) support is a minor feature advantage, but it does not translate into any benchmark wins. Ultimately, the GTX 650 Ti Boost is the winner in compute performance, while the R9 M360's niche is limited to capacity-oriented tasks.