AMD Radeon R7 M380 vs NVIDIA GeForce GTX 1070 Comparison

NVIDIA GeForce GTX 1070 vs AMD Radeon R7 M380 is a comparison between two end-of-life GPUs from different eras and market segments. The data shows a decisive overall performance gap: the GTX 1070 holds an average benchmark score of 9780, while the R7 M380 scores 9313. However, the GTX 1070 sits in the 47th percentile of all GPUs, and the R7 M380 is in the 46th, placing both in the mid-range of the overall performance distribution despite the absolute score difference.

Where Each One Wins

The GTX 1070 wins the only head-to-head benchmark available, Geekbench OpenCL, by a massive margin. It scores 44700 against the R7 M380's 9313, a delta of 380%. This is not a close contest; the GTX 1070 is in a completely different performance tier. In the broader benchmark suite, the GTX 1070 has results across multiple test types, including 3DMark Steel Nomad (1082), Geekbench Metal (18801), Geekbench Vulkan (22121), and Passmark G3D (13498). The R7 M380 has only a single benchmark entry, Geekbench OpenCL, which makes direct comparisons in other workloads impossible from the data.

The R7 M380’s only "win" is that it exists in a lower performance bracket. Its nearest rivals include the NVIDIA GeForce GTX 850M (avg score 9302, delta 0.1%), the GeForce GTX 465 (9294, delta 0.2%), and the GeForce GTX 960 (9273, delta 0.4%). This places it alongside older or lower-tier discrete mobile GPUs. The GTX 1070’s nearest rivals are very different: the AMD FirePro W5000 (avg 9803, delta -0.2%), Quadro M2000M (9832, delta -0.5%), Tesla M10 (9724, delta 0.6%), and Tesla C2070 (9716, delta 0.7%). These are professional or workstation-class cards, indicating the GTX 1070 competes at a much higher performance level.

For practical use, the GTX 1070 is the clear choice for any compute-heavy or gaming workload that leverages OpenCL, DirectX, or Vulkan. The R7 M380, based on its single benchmark and rival positioning, is suited only for light, legacy tasks where its lower performance is acceptable. There is no scenario in the provided data where the R7 M380 outperforms the GTX 1070.

Architecture Differences

The two GPUs come from different architectural generations and process nodes. The GTX 1070 uses the NVIDIA GP104 chip built on Pascal architecture, fabricated on a 16 nm process at TSMC. It packs 7,200 million transistors on a 314 mm² die, resulting in a transistor density of 22.9M per mm². The R7 M380 uses the AMD Tropo chip based on GCN 1.0 architecture, built on an older 28 nm process, also at TSMC. It contains 1,500 million transistors on a 123 mm² die, with a lower density of 12.2M per mm².

Core configurations differ substantially. The GTX 1070 has 1920 shading units, 120 texture mapping units (TMUs), and 64 raster output units (ROPs). The R7 M380 has 640 shading units, 40 TMUs, and 16 ROPs. These numbers directly explain the massive fill rate and compute differences: the GTX 1070 achieves a pixel rate of 107.7 GPixel/s and texture rate of 202.0 GTexel/s, while the R7 M380 manages only 14.64 GPixel/s and 36.60 GTexel/s.

Memory architecture is also divergent. The GTX 1070 uses 8 GB of GDDR5 on a 256-bit bus, delivering 256.3 GB/s of bandwidth. The R7 M380 uses 4 GB of DDR3 on a 128-bit bus, delivering just 32.00 GB/s. Clock speeds differ as well: the GTX 1070 runs at a base of 1506 MHz and boost of 1683 MHz, while the R7 M380 operates at 900 MHz base and 915 MHz boost. The GTX 1070’s memory runs at 2002 MHz (8 Gbps effective), whereas the R7 M380’s memory is at 1000 MHz (2 Gbps effective).

API support shows a small gap. The GTX 1070 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The R7 M380 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The GTX 1070 also has a higher FP32 compute rating at 6.463 TFLOPS, compared to the R7 M380’s 1,171.2 GFLOPS. The GTX 1070 has a specified FP16 rate of 101.0 GFLOPS (1:64), while the R7 M380 has no FP16 data.

Head-to-Head Benchmarks

The single head-to-head benchmark result is decisive. In Geekbench OpenCL, the NVIDIA GeForce GTX 1070 scores 44700, while the AMD Radeon R7 M380 scores 9313. The delta is 380% in favor of the GTX 1070. This is not a marginal win; it is a multi-generational leap in compute performance.

To contextualize this within their respective rival groups: the GTX 1070’s average score of 9780 is only 0.2% below the AMD FirePro W5000 (9803) and 0.5% below the Quadro M2000M (9832). It is 0.6% above the Tesla M10 (9724) and 0.7% above the Tesla C2070 (9716). This shows the GTX 1070 is tightly clustered with professional GPUs in overall average performance, though the OpenCL result specifically is far higher than its own average, suggesting it excels particularly in compute workloads.

The R7 M380’s average score of 9313 is just 0.1% above the GeForce GTX 850M (9302) and 0.2% above the GTX 465 (9294). It is 0.4% above the GTX 960 (9273) and 1% above the Radeon Vega 8 (9221). In its own tier, the R7 M380 is at the top, but that tier is far below the GTX 1070. The 380% delta in OpenCL means the GTX 1070 delivers nearly five times the raw compute throughput in that specific test.

Other GTX 1070 benchmarks reinforce its strength, but no comparable R7 M380 scores exist for those tests. The GTX 1070’s Passmark G3D score is 13498, its Passmark GPU Compute score is 6102, and its 3DMark Steel Nomad DX12 score is 1082. These numbers cannot be directly compared to the R7 M380, but they indicate a well-rounded GPU across DirectX 9, 10, 11, and 12 tests, with scores of 197, 82, 100, and 48 respectively.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce GTX 1070 has an average benchmark score of 9780, compared to the AMD Radeon R7 M380’s 9313. This places the GTX 1070 at the 47th percentile of all GPUs and the R7 M380 at the 46th percentile.

Q: How much faster is the GTX 1070 in the only shared benchmark?

A: In Geekbench OpenCL, the GTX 1070 scores 44700 versus the R7 M380’s 9313, a delta of 380%. This means the GTX 1070 is 3.8 times faster in that specific compute test.

Q: What are the nearest rivals for each GPU?

A: The GTX 1070’s nearest rivals are the AMD FirePro W5000 (9803, -0.2%), Quadro M2000M (9832, -0.5%), Tesla M10 (9724, 0.6%), and Tesla C2070 (9716, 0.7%). The R7 M380’s nearest rivals are the GeForce GTX 850M (9302, 0.1%), GTX 465 (9294, 0.2%), GTX 960 (9273, 0.4%), and Radeon Vega 8 (9221, 1%).

Q: Do both GPUs support the same DirectX version?

A: No. The GTX 1070 supports DirectX 12 (12_1), while the R7 M380 supports DirectX 12 (11_1). Both support OpenGL 4.6, but the GTX 1070 supports Vulkan 1.4 versus the R7 M380’s Vulkan 1.2.170.

Q: What is the memory bandwidth difference?

A: The GTX 1070 has a memory bandwidth of 256.3 GB/s using 8 GB of GDDR5 on a 256-bit bus. The R7 M380 has 32.00 GB/s using 4 GB of DDR3 on a 128-bit bus. That is an 8x difference in bandwidth.

Q: Which GPU has more shading units?

A: The GTX 1070 has 1920 shading units, while the R7 M380 has 640. The GTX 1070 also has 120 TMUs and 64 ROPs, versus the R7 M380’s 40 TMUs and 16 ROPs.

The Verdict

The data is unambiguous. The NVIDIA GeForce GTX 1070 is the superior GPU in every measurable aspect provided. It wins the only head-to-head benchmark by 380%, has a higher average score (9780 vs 9313), and offers more than three times the shading units (1920 vs 640). Architecturally, it is built on a newer 16 nm process versus 28 nm, has a larger die (314 mm² vs 123 mm²), and uses faster GDDR5 memory with 8x the bandwidth (256.3 GB/s vs 32.00 GB/s).

For a user choosing between these two, the GTX 1070 is the only rational pick for any modern workload involving DirectX 12, Vulkan, or OpenCL compute. Its 6.463 TFLOPS FP32 performance and 107.7 GPixel/s pixel rate put it in a different class than the R7 M380’s 1,171.2 GFLOPS and 14.64 GPixel/s. The R7 M380’s only advantage is its smaller die size (123 mm² vs 314 mm²) and lower transistor count (1,500 million vs 7,200 million), which implies lower power draw, though no TDP data is provided for the R7 M380.

The GTX 1070’s nearest rivals are professional cards like the FirePro W5000 and Quadro M2000M, whereas the R7 M380 competes with older GeForce GTX 800/900-series mobile parts. If the choice is between these two specific GPUs, the GTX 1070 is the definitive winner. The R7 M380 should only be considered if the system absolutely requires a smaller, simpler board with no external power connector — but even then, performance will be a fraction of the GTX 1070.

Specification Differences

| Specification | NVIDIA GeForce GTX 1070 | AMD Radeon R7 M380 |

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

| Chip | GP104 | Tropo |

| Architecture | Pascal | GCN 1.0 |

| Process Node | 16 nm | 28 nm |

| Transistors | 7,200 million | 1,500 million |

| Die Size | 314 mm² | 123 mm² |

| Transistor Density | 22.9M / mm² | 12.2M / mm² |

| Base Clock | 1506 MHz | 900 MHz |

| Boost Clock | 1683 MHz | 915 MHz |

| Memory Clock | 2002 MHz (8 Gbps effective) | 1000 MHz (2 Gbps effective) |

| Memory Size | 8 GB | 4 GB |

| Memory Type | GDDR5 | DDR3 |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 256.3 GB/s | 32.00 GB/s |

| Shading Units | 1920 | 640 |

| TMUs | 120 | 40 |

| ROPs | 64 | 16 |

| Pixel Rate | 107.7 GPixel/s | 14.64 GPixel/s |

| Texture Rate | 202.0 GTexel/s | 36.60 GTexel/s |

| FP32 Performance | 6.463 TFLOPS | 1,171.2 GFLOPS |

| FP16 Performance | 101.0 GFLOPS (1:64) | null |

| TDP | 150 W | null |

| Power Connectors | 1x 8-pin | null |

| DirectX Support | 12 (12_1) | 12 (11_1) |

| Vulkan Support | 1.4 | 1.2.170 |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.4a | null |

| Dimensions | 267 mm (10.5 in) length, 112 mm (4.4 in) height, 40 mm (1.6 in) width | null |

| Release Date | 2016-06-09 | 2015-05-04 |

| Launch MSRP | 379 USD | null |

| Predecessor | GeForce 900 | Solar System |

| Successor | GeForce 20 | Polaris Mobile |

| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |

| Slot Width | Dual-slot | null |

| Suggested PSU | 450 W | null |