AMD Radeon R7 M380 vs NVIDIA GeForce GTX 650 Ti Boost Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark recorded for both GPUs is Geekbench OpenCL, and the result is remarkably close. The AMD Radeon R7 M380 scores 9,313, while the NVIDIA GeForce GTX 650 Ti Boost scores 9,302. That is a delta of just 0.1% in favor of the AMD part, effectively a statistical tie in compute throughput. The data shows that in raw OpenCL compute, neither card holds a meaningful advantage, and the difference would be imperceptible in real-world workloads that rely on this API.

However, the broader benchmark picture reveals a different story. The GTX 650 Ti Boost has three recorded benchmark entries: Geekbench OpenCL at 9,302, Geekbench Vulkan at 10,041, and Geekbench Metal at 4,858. Its average benchmark score across all tests is 8,067. The R7 M380 has only one recorded benchmark, the OpenCL result, which also serves as its average score of 9,313. This means the NVIDIA card's average is pulled down significantly by the Metal result, which is an Apple-specific API and not relevant to the typical Windows or Linux usage of these desktop or mobile parts. If we compare only the common OpenCL test, the AMD card is ahead by 11 points, but the NVIDIA card's Vulkan score of 10,041 is 7.8% higher than the AMD card's OpenCL score, suggesting that in Vulkan workloads the NVIDIA architecture may have an edge, though no direct Vulkan comparison exists between the two.

Looking at percentile placement, the R7 M380 sits at the 46th percentile of all GPUs, while the GTX 650 Ti Boost sits at the 42nd percentile. This is a modest but real separation in overall standing, driven primarily by the fact that the AMD card has a higher single-test score than the NVIDIA card's average. The nearest rivals for the R7 M380 include the NVIDIA GeForce GTX 850M at 9,302 (0.1% behind), the NVIDIA GeForce GTX 465 at 9,294 (0.2% behind), the NVIDIA GeForce GTX 960 at 9,273 (0.4% behind), and the AMD Radeon Vega 8 at 9,221 (1% behind). The GTX 650 Ti Boost's nearest rivals are the NVIDIA GRID K2 at 8,080 (0.2% behind in the negative direction, meaning the 650 Ti Boost is actually ahead), the NVIDIA GeForce GTX 650 Ti at 8,053 (0.2% ahead), the NVIDIA GeForce GTX 880M at 8,040 (0.3% ahead), and the NVIDIA Quadro P5000 at 8,039 (0.3% ahead). This shows that the R7 M380 competes in a higher performance tier than the GTX 650 Ti Boost, despite their near-identical OpenCL scores, because the NVIDIA card's average is diluted by its Metal result.

Where Each One Wins

The AMD Radeon R7 M380 wins the only direct head-to-head benchmark, the Geekbench OpenCL test, by a hair. This suggests that for compute workloads that are optimized for OpenCL, the R7 M380 is marginally ahead. Its higher average benchmark score of 9,313 compared to the GTX 650 Ti Boost's 8,067 also indicates that, on a per-test basis, the AMD card delivers more consistent compute performance across the tests it has been subjected to. The R7 M380 also has a higher percentile ranking, 46 versus 42, which places it above a larger fraction of the GPU population.

The NVIDIA GeForce GTX 650 Ti Boost wins in the Vulkan API test, scoring 10,041, which is higher than any score recorded for the R7 M380. While no direct Vulkan comparison exists, the data shows that the NVIDIA card is capable of substantially higher throughput in Vulkan workloads. The GTX 650 Ti Boost also has a much higher memory bandwidth, 144.2 GB/s versus 32.00 GB/s, which would give it a significant advantage in bandwidth-bound scenarios such as high-resolution texture streaming or compute kernels that access large data arrays. Additionally, the NVIDIA card has a higher pixel rate (16.51 GPixel/s versus 14.64 GPixel/s) and a dramatically higher texture rate (66.05 GTexel/s versus 36.60 GTexel/s), indicating that in rasterization-heavy tasks like traditional gaming, the GTX 650 Ti Boost should pull ahead despite the near-parity in OpenCL compute.

The R7 M380, however, has double the memory capacity (4 GB versus 2 GB), which is an advantage in workloads that require large working sets, such as certain machine learning inference tasks or rendering scenes with many textures. The AMD card also supports DirectX 12 (11_1) versus the NVIDIA card's DirectX 12 (11_0), which is a minor feature advantage for newer titles that leverage 11_1 features. For the use case of a user who primarily runs OpenCL compute and needs large memory buffers, the R7 M380 is the better choice. For a user who prioritizes Vulkan performance, texture throughput, or raw memory bandwidth, the GTX 650 Ti Boost is superior.

Architecture Differences

The AMD Radeon R7 M380 is built on the GCN 1.0 architecture using the Tropo chip, fabricated on a 28 nm process at TSMC. The die is 123 mm² and contains 1,500 million transistors, giving a transistor density of 12.2 million per square millimeter. The NVIDIA GeForce GTX 650 Ti Boost uses the Kepler architecture with the GK106 chip, also on TSMC's 28 nm process, but the die is substantially larger at 221 mm² and contains 2,540 million transistors, for a density of 11.5 million per square millimeter. The NVIDIA chip is both physically larger and denser in absolute transistor count, but the AMD chip is slightly more efficient in packing transistors per area.

The R7 M380 has 640 shading units, 40 texture mapping units, and 16 raster output units. The GTX 650 Ti Boost has 768 shading units, 64 TMUs, and 24 ROPs. The NVIDIA card has more of every execution resource, which explains its higher texture rate (66.05 GTexel/s versus 36.60 GTexel/s) and pixel rate (16.51 GPixel/s versus 14.64 GPixel/s). However, the AMD card's FP32 compute throughput is 1,171.2 GFLOPS, while the NVIDIA card is rated at 1.585 TFLOPS, or 1,585 GFLOPS. So the NVIDIA card is about 35% higher in raw floating-point compute, yet the OpenCL benchmark shows them nearly tied. This suggests that the AMD GCN architecture extracts more real-world compute performance per theoretical FLOP, or that the OpenCL driver implementation on the AMD side is more efficient.

Memory architecture is drastically different. The R7 M380 uses 4 GB of DDR3 on a 128-bit bus, yielding 32.00 GB/s of bandwidth. The GTX 650 Ti Boost uses 2 GB of GDDR5 on a 192-bit bus, yielding 144.2 GB/s, which is 4.5 times higher bandwidth. Clock speeds also differ: the AMD card runs at a base of 900 MHz with a boost of 915 MHz, while the NVIDIA card runs at 980 MHz base and 1032 MHz boost. The memory clock on the AMD card is 1000 MHz (2 Gbps effective), while the NVIDIA card runs at 1502 MHz (6 Gbps effective). The NVIDIA card has a TDP of 134 W, requires a single 6-pin power connector, and needs a 300 W power supply, whereas the R7 M380 has no TDP listed in the database. The GTX 650 Ti Boost is a dual-slot card measuring 241 mm (9.5 inches) in length, while the R7 M380 has no dimensions recorded.

Both cards support PCIe 3.0 x16. The AMD card supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA card supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The NVIDIA card has display outputs of 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the R7 M380's display outputs are not recorded. The R7 M380 is from the Gem System (R7 M300) generation and is considered a mobile part, whereas the GTX 650 Ti Boost is from the GeForce 600 generation and is a desktop card. The R7 M380's predecessor is Solar System and successor is Polaris Mobile; the GTX 650 Ti Boost's predecessor is GeForce 500 and successor is GeForce 700.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R7 M380 has an average benchmark score of 9,313, while the NVIDIA GeForce GTX 650 Ti Boost has an average of 8,067. The AMD card's average is higher because the NVIDIA card's average is reduced by its Geekbench Metal score of 4,858.

Q: How do the two GPUs compare in the Geekbench OpenCL test?

A: The AMD Radeon R7 M380 scores 9,313, and the NVIDIA GeForce GTX 650 Ti Boost scores 9,302. The AMD card wins by 0.1%, which is effectively a tie.

Q: Does the NVIDIA card have any benchmark where it clearly outperforms the AMD card?

A: Yes, the NVIDIA GeForce GTX 650 Ti Boost scores 10,041 in Geekbench Vulkan, which is 7.8% higher than the AMD card's OpenCL score. This is the highest recorded benchmark result between the two.

Q: What is the memory bandwidth difference?

A: The NVIDIA GeForce GTX 650 Ti Boost has a memory bandwidth of 144.2 GB/s, while the AMD Radeon R7 M380 has 32.00 GB/s. The NVIDIA card has 4.5 times the bandwidth.

Q: Which GPU has more shading units and texture units?

A: The NVIDIA GeForce GTX 650 Ti Boost has 768 shading units, 64 TMUs, and 24 ROPs. The AMD Radeon R7 M380 has 640 shading units, 40 TMUs, and 16 ROPs.

Q: What is the percentile ranking for each GPU?

A: The AMD Radeon R7 M380 is at the 46th percentile of all GPUs, while the NVIDIA GeForce GTX 650 Ti Boost is at the 42nd percentile.

Specification Differences

The table below highlights only the fields where the two GPUs differ, based on the recorded data.

| Specification | AMD Radeon R7 M380 | NVIDIA GeForce GTX 650 Ti Boost |

|---------------|-------------------|--------------------------------|

| Architecture | GCN 1.0 | Kepler |

| Chip | Tropo | GK106 |

| Generation | Gem System (R7 M300) | GeForce 600 |

| Transistors | 1,500 million | 2,540 million |

| Die Size | 123 mm² | 221 mm² |

| Transistor Density | 12.2M / mm² | 11.5M / mm² |

| Base Clock | 900 MHz | 980 MHz |

| Boost Clock | 915 MHz | 1032 MHz |

| Memory Clock | 1000 MHz (2 Gbps effective) | 1502 MHz (6 Gbps effective) |

| Memory Size | 4 GB | 2 GB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 128 bit | 192 bit |

| Memory Bandwidth | 32.00 GB/s | 144.2 GB/s |

| Shading Units | 640 | 768 |

| TMUs | 40 | 64 |

| ROPs | 16 | 24 |

| Pixel Rate | 14.64 GPixel/s | 16.51 GPixel/s |

| Texture Rate | 36.60 GTexel/s | 66.05 GTexel/s |

| FP32 | 1,171.2 GFLOPS | 1.585 TFLOPS |

| TDP | Not listed | 134 W |

| Slot Width | Not listed | Dual-slot |

| Power Connectors | Not listed | 1x 6-pin |

| Suggested PSU | Not listed | 300 W |

| Display Outputs | Not listed | 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 |

| DirectX | 12 (11_1) | 12 (11_0) |

| Vulkan | 1.2.170 | 1.2.175 |

| Dimensions (Length) | Not listed | 241 mm (9.5 inches) |

| Release Date | 2015-05-04 | 2013-03-25 |

| Predecessor | Solar System | GeForce 500 |

| Successor | Polaris Mobile | GeForce 700 |

| Launch MSRP | Not listed | 169 USD |

| Geekbench OpenCL Score | 9,313 | 9,302 |

| Geekbench Vulkan Score | Not listed | 10,041 |

| Geekbench Metal Score | Not listed | 4,858 |

| Average Benchmark Score | 9,313 | 8,067 |

| Percentile vs All GPUs | 46 | 42 |