AMD Radeon R7 M380 vs AMD Radeon Vega 8 Comparison

The AMD Radeon R7 M380 and AMD Radeon Vega 8 are two very different interpretations of mobile graphics, separated by nearly three years of architectural evolution. The data shows a narrow overall victory for the older discrete part, with the R7 M380 averaging a benchmark score of 9313 compared to the Vega 8’s 9221, a 1% difference. However, the story is far more nuanced than a single aggregate number, as the Vega 8’s newer architecture and feature set present a compelling counter-argument despite losing the specific head-to-head test.

The Verdict

Based strictly on the benchmark data, the AMD Radeon R7 M380 is the faster GPU in raw compute performance. It wins the sole head-to-head OpenCL benchmark with a score of 9313 against the Vega 8’s 8822, a decisive 5.6% advantage. This makes it the clear choice for users prioritizing raw computational throughput in applications that leverage OpenCL. Its position in the broader market also reflects this, as it sits at the 46th percentile of all GPUs, just one spot above the Vega 8’s 45th percentile.

However, the AMD Radeon Vega 8 is not without its own merits. While it loses the OpenCL test, it demonstrates superior performance in other API workloads. Its Geekbench Metal score of 10706 and Vulkan score of 8134 show that it is a more versatile modern compute device. For users working within the Metal or Vulkan ecosystems, the Vega 8 is demonstrably stronger. The choice ultimately depends on the software environment: the R7 M380 is the pick for OpenCL-centric tasks, while the Vega 8 is better suited for applications that utilize Metal or Vulkan. The R7 M380 also offers a dedicated 4 GB memory pool, which can be an advantage in scenarios where system memory bandwidth is a bottleneck.

Architecture Differences

The two GPUs represent distinct generations of AMD’s Graphics Core Next architecture. The R7 M380 is built on the older GCN 1.0 architecture, using the Tropo chip manufactured on a 28 nm process at TSMC. In contrast, the Vega 8 utilizes the much newer GCN 5.0 architecture with the Raven chip, fabricated by GlobalFoundries on a more advanced 14 nm process. This process advantage is substantial, allowing the Vega 8’s die to pack 4,940 million transistors into a 210 mm² area, achieving a transistor density of 23.5 million per square millimeter. The R7 M380, by comparison, has only 1,500 million transistors on a 123 mm² die, for a density of 12.2 million per square millimeter.

The architectural gap also translates into feature support. The Vega 8 supports DirectX 12 (12_1) and Vulkan 1.3, while the R7 M380 is limited to DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6. The Vega 8 also has a significant advantage in half-precision compute, offering 2.253 TFLOPS of FP16 performance with a 2:1 ratio, a feature entirely absent from the R7 M380’s specifications. This makes the Vega 8 much more capable in modern workloads that can leverage mixed-precision computing.

Head-to-Head Benchmarks

The only direct benchmark comparison available is the Geekbench OpenCL test, and the results are clear. The AMD Radeon R7 M380 scores 9313, defeating the AMD Radeon Vega 8’s score of 8822 by a margin of 5.6%. This is a significant victory, showcasing the R7 M380’s superior raw compute power in this specific API. The R7 M380’s advantage here can be attributed to its higher base and boost clocks, which are 900 MHz and 915 MHz respectively, compared to the Vega 8’s 300 MHz base and 1100 MHz boost. While the Vega 8 has a higher boost clock, its base clock is much lower, and the R7 M380 likely sustains a higher average frequency under load.

Despite losing the OpenCL test, the Vega 8 shows its strength in other benchmark suites. Its Geekbench Metal score of 10706 is higher than its OpenCL score, and its Vulkan score of 8134, while lower, still demonstrates a capable modern API implementation. The R7 M380 has no Metal or Vulkan scores listed, suggesting it is not a viable option for those workloads. This data indicates that while the R7 M380 is the absolute winner in OpenCL, the Vega 8 is the more well-rounded GPU for a variety of modern compute APIs.

Specification Differences

Beyond the architectural and process node differences, the two GPUs diverge significantly in their physical and memory specifications.

• Process Node: The R7 M380 uses a 28 nm process from TSMC, while the Vega 8 uses a 14 nm process from GlobalFoundries.
• Transistors: The R7 M380 has 1,500 million transistors, while the Vega 8 has 4,940 million.
• Die Size: The R7 M380 has a 123 mm² die, while the Vega 8 has a 210 mm² die.
• Transistor Density: The R7 M380 has a density of 12.2 million transistors per mm², while the Vega 8 has 23.5 million per mm².
• Base Clock: The R7 M380 runs at 900 MHz, while the Vega 8 runs at a much lower 300 MHz.
• Boost Clock: The R7 M380 boosts to 915 MHz, while the Vega 8 boosts to 1100 MHz.
• Memory Size: The R7 M380 has a dedicated 4 GB of DDR3 memory, while the Vega 8 uses System Shared memory.
• Memory Type: The R7 M380 uses DDR3, while the Vega 8 uses System Shared memory.
• Memory Bus Width: The R7 M380 has a 128-bit bus, while the Vega 8’s is System Shared.
• Memory Bandwidth: The R7 M380 has a fixed 32.00 GB/s bandwidth, while the Vega 8’s is System Dependent.
• Shading Units: The R7 M380 has 640 shading units, while the Vega 8 has 512.
• TMUs: The R7 M380 has 40 texture mapping units, while the Vega 8 has 32.
• ROPs: The R7 M380 has 16 render output units, while the Vega 8 has 8.
• Pixel Rate: The R7 M380 achieves 14.64 GPixel/s, while the Vega 8 achieves 8.800 GPixel/s.
• Texture Rate: The R7 M380 achieves 36.60 GTexel/s, while the Vega 8 achieves 35.20 GTexel/s.
• FP32 Performance: The R7 M380 delivers 1,171.2 GFLOPS, while the Vega 8 delivers 1,126.4 GFLOPS.
• FP16 Performance: The R7 M380 has no listed FP16 performance, while the Vega 8 delivers 2.253 TFLOPS.
• TDP: The R7 M380 has no listed TDP, while the Vega 8 is rated at 25 W.
• Power Connectors: The R7 M380 has no listed power connectors, while the Vega 8 has None.
• Bus Interface: The R7 M380 uses PCIe 3.0 x16, while the Vega 8 uses an IGP interface.
• Display Outputs: The R7 M380 has no listed display outputs, while the Vega 8 is Motherboard Dependent.
• DirectX Support: The R7 M380 supports DirectX 12 (11_1), while the Vega 8 supports DirectX 12 (12_1).
• Vulkan Support: The R7 M380 supports Vulkan 1.2.170, while the Vega 8 supports Vulkan 1.3.
• Release Date: The R7 M380 was released on 2015-05-04, while the Vega 8 was released on 2018-02-11.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL benchmark?

A: The AMD Radeon R7 M380 is faster, scoring 9313 compared to the AMD Radeon Vega 8’s 8822, a 5.6% difference.

Q: Does the AMD Radeon Vega 8 perform better in any benchmarks?

A: Yes. The Vega 8 scores 10706 in Geekbench Metal and 8134 in Geekbench Vulkan, benchmarks in which the R7 M380 has no recorded scores.

Q: What is the primary architectural difference between the two GPUs?

A: The R7 M380 uses the older GCN 1.0 architecture on a 28 nm TSMC process, while the Vega 8 uses the newer GCN 5.0 architecture on a 14 nm GlobalFoundries process.

Q: How does the memory configuration differ?

A: The R7 M380 has a dedicated 4 GB of DDR3 memory on a 128-bit bus with 32.00 GB/s bandwidth. The Vega 8 uses System Shared memory with a bandwidth that is System Dependent.

Q: Which GPU has a higher boost clock speed?

A: The AMD Radeon Vega 8 has a higher boost clock of 1100 MHz, compared to the R7 M380’s 915 MHz. However, the R7 M380 has a much higher base clock of 900 MHz versus the Vega 8’s 300 MHz.

Q: What is the difference in their production status?

A: Both GPUs are listed as End-of-life. The R7 M380 was released on 2015-05-04, and the Vega 8 was released later on 2018-02-11.