AMD Radeon R7 M370 vs Intel Iris Pro Graphics P580 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The Intel Iris Pro Graphics P580 holds a higher average benchmark score of 7170, compared to the AMD Radeon R7 M370's 6764. This places the Intel part at the 39th percentile of all GPUs, while the AMD part sits at the 38th percentile.

Q: How do the two GPUs compare in OpenCL performance?

A: The Intel Iris Pro Graphics P580 is decisively ahead in Geekbench OpenCL, scoring 9082 against the AMD Radeon R7 M370's 7063. That is a 28.6% advantage for the Intel solution in this compute-oriented workload.

Q: Does the AMD Radeon R7 M370 win any benchmark?

A: Yes, the AMD Radeon R7 M370 wins the Geekbench Vulkan test with a score of 6465, while the Intel Iris Pro Graphics P580 scores 5258. The AMD part leads by 18.7% in this API-specific test.

Q: What are the process node differences between the two chips?

A: The Intel Iris Pro Graphics P580 is built on Intel's 14 nm+ process, while the AMD Radeon R7 M370 uses TSMC's 28 nm process. The Intel chip is integrated into the Skylake GT4e die, whereas the AMD chip is a discrete part with 950 million transistors on a 77 mm² die.

Q: Which GPU supports a higher DirectX version?

A: The Intel Iris Pro Graphics P580 supports DirectX 12 (12_1), while the AMD Radeon R7 M370 supports DirectX 12 (11_1). Both support OpenGL 4.6, but the Intel part also supports Vulkan 1.3 versus Vulkan 1.2.170 on the AMD part.

Q: How do their nearest rivals compare in average score?

A: The Intel GPU's closest rival is the NVIDIA GeForce GTX 560 SE with an average score of 7171 (a 0% delta), while the AMD GPU's nearest rival is the AMD FirePro M5100 with an average score of 6830 (a -1% delta). The Intel part's rivals also include the NVIDIA GeForce GTX 970 at 7157 (0.2% delta) and the AMD Radeon Vega 8 Mobile at 7203 (-0.5% delta).

Architecture Differences

The fundamental architectural split here is stark: the Intel Iris Pro Graphics P580 is an integrated GPU built on the Skylake GT4e chip using Intel's Generation 9.0 architecture, while the AMD Radeon R7 M370 is a discrete mobile part based on the Litho chip using GCN 1.0. These are different design philosophies from different vendors, and the data reflects that.

The process node tells a significant story. Intel uses a 14 nm+ process from its own foundry, whereas AMD relies on TSMC's 28 nm process. This manufacturing gap—two full generations in lithography—allows Intel to pack more compute resources into a smaller power envelope, even if the AMD chip has a larger physical presence with its 950 million transistors spread across 77 mm².

Shader resources differ meaningfully. The Intel part carries 576 shading units, 72 texture mapping units, and 9 ROPs. The AMD part has fewer shading units at 384, fewer TMUs at 24, and 8 ROPs. This configuration gives Intel a theoretical pixel rate of 9.000 GPixel/s and a texture rate of 72.00 GTexel/s, versus AMD's 7.680 GPixel/s and 23.04 GTexel/s. The TMU gap is particularly wide—Intel has three times the texture units, which explains its dominant texture fill rate.

Memory architecture could not be more different. The Intel Iris Pro Graphics P580 uses system shared memory with system-dependent bandwidth, while the AMD Radeon R7 M370 has dedicated 2 GB of GDDR5 on a 128-bit bus, delivering 57.60 GB/s of bandwidth. This dedicated memory gives the AMD part a potential advantage in memory-sensitive scenarios, though the shared-memory approach on the Intel side benefits from the CPU's memory controller.

Compute throughput also diverges. Intel's FP32 performance is 1,152.0 GFLOPS, and it even provides FP16 at 2.304 TFLOPS with a 2:1 ratio. The AMD part delivers 737.3 GFLOPS of FP32 and lists no FP16 capability. The bus interface differs too: Intel connects via Ring Bus (typical for integrated graphics), while AMD uses PCIe 3.0 x8.

Where Each One Wins

The benchmark data splits cleanly by workload type. The Intel Iris Pro Graphics P580 dominates in OpenCL compute, suggesting it excels in general-purpose GPU compute tasks, physics simulations, and applications that leverage OpenCL for acceleration. Its 28.6% lead in this test is substantial and points to the raw compute horsepower of its 576 shading units and superior texture throughput.

The AMD Radeon R7 M370, by contrast, wins in Vulkan. This is notable because Vulkan is a lower-overhead graphics API that stresses driver efficiency and memory management. The AMD part's 18.7% lead here suggests it handles modern graphics API workloads more effectively, potentially benefiting from its dedicated GDDR5 memory and its GCN architecture's maturity with graphics-oriented tasks.

For gaming, the Vulkan result is more relevant, as many modern titles support Vulkan. The AMD part's victory there indicates it may deliver smoother frame pacing in Vulkan-based games. For productivity and compute tasks, the Intel part's OpenCL lead makes it the stronger choice for video encoding, image processing, or scientific workloads that use OpenCL.

The average benchmark scores reinforce this split. Intel's average of 7170 versus AMD's 6764 shows Intel has the higher overall ceiling, but the Vulkan gap shows AMD is not without merit in specific scenarios. The percentile rankings are close—39th for Intel, 38th for AMD—suggesting both are mid-tier performers in the broader GPU landscape.

Specification Differences

| Specification | Intel Iris Pro Graphics P580 | AMD Radeon R7 M370 |

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

| Process Node | 14 nm+ | 28 nm |

| Foundry | Intel | TSMC |

| Transistors | Not listed | 950 million |

| Die Size | Not listed | 77 mm² |

| Base Clock | 350 MHz | 875 MHz |

| Boost Clock | 1000 MHz | 960 MHz |

| Memory Size | System Shared | 2 GB |

| Memory Type | System Shared | GDDR5 |

| Memory Bus | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 57.60 GB/s |

| Shading Units | 576 | 384 |

| TMUs | 72 | 24 |

| ROPs | 9 | 8 |

| Pixel Rate | 9.000 GPixel/s | 7.680 GPixel/s |

| Texture Rate | 72.00 GTexel/s | 23.04 GTexel/s |

| FP32 | 1,152.0 GFLOPS | 737.3 GFLOPS |

| FP16 | 2.304 TFLOPS (2:1) | Not listed |

| TDP | 15 W | Not listed |

| Bus Interface | Ring Bus | PCIe 3.0 x8 |

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

| Vulkan | 1.3 | 1.2.170 |

| Release Date | 2015-08-31 | 2015-05-04 |

The clock speeds tell a curious story. The AMD part has a much higher base clock at 875 MHz versus Intel's 350 MHz, and its boost clock of 960 MHz is close to Intel's 1000 MHz boost. Yet Intel still achieves higher compute throughput, which confirms its wider execution resources and newer process node.

Head-to-Head Benchmarks

The Geekbench OpenCL test is the single largest differentiator between these two GPUs. Intel scores 9082 against AMD's 7063, a delta of 28.6% in favor of the Intel Iris Pro Graphics P580. This is not a marginal win; it is a decisive margin that reflects the Intel part's advantages in shading units (576 vs 384), texture units (72 vs 24), and FP32 throughput (1,152.0 GFLOPS vs 737.3 GFLOPS). The texture rate difference is particularly telling—Intel's 72.00 GTexel/s is more than triple AMD's 23.04 GTexel/s, which directly impacts compute workloads that rely on texture sampling.

The Geekbench Vulkan test flips the narrative. AMD scores 6465 against Intel's 5258, giving the Radeon R7 M370 an 18.7% lead. This is a significant victory for AMD, and it suggests that the dedicated GDDR5 memory with 57.60 GB/s bandwidth provides a tangible benefit in Vulkan workloads. The Intel part's system-shared memory, with bandwidth described as "System Dependent," may become a bottleneck in API-level graphics operations that demand consistent memory access.

Looking at the nearest rivals for context, the Intel part's average score of 7170 sits almost exactly between the NVIDIA GeForce GTX 560 SE (7171, 0% delta) and the NVIDIA GeForce GTX 970 (7157, 0.2% delta). This places Intel's integrated solution in surprising company—it trades blows with dedicated desktop GPUs from NVIDIA. The AMD Radeon R7 M370's average of 6764 puts it ahead of the NVIDIA GeForce GT 1010 (6698, 1% delta) but behind the AMD Radeon R7 M460 (6612, 2.3% delta) is not a rival—rather, the M370 leads the M460 by 2.3% based on the delta values listed.

The Verdict

The data presents a clear choice depending on the use case. For compute-heavy applications that leverage OpenCL—think video processing, 3D rendering, or scientific computing—the Intel Iris Pro Graphics P580 is the superior option. Its 28.6% OpenCL lead over the AMD Radeon R7 M370 is substantial, and its higher FP32 throughput and triple the texture units provide a solid foundation for parallel compute tasks.

For gaming or applications that favor the Vulkan API, the AMD Radeon R7 M370 is the better pick. Its 18.7% Vulkan advantage, backed by dedicated 2 GB GDDR5 memory with 57.60 GB/s bandwidth, suggests smoother performance in modern Vulkan-based titles. The discrete memory configuration also makes it more predictable in memory-constrained scenarios, as it does not depend on system memory bandwidth.

The average benchmark score favors Intel (7170 vs 6764), and the percentile rankings are nearly identical (39th vs 38th). This tells a nuanced story: Intel has the higher overall compute ceiling, but AMD has carved out a specific niche where it excels. The one-win-each split in the head-to-head benchmarks is a reminder that "better" depends entirely on the workload.

Users who need a jack-of-all-trades integrated GPU with strong compute performance should look to the Intel Iris Pro Graphics P580. Users who prioritize Vulkan gaming and want the benefits of dedicated VRAM should consider the AMD Radeon R7 M370. The data does not crown a single winner—it defines two distinct domains of superiority, and the right choice hinges on which benchmark aligns with your primary applications.