AMD Radeon R5 M320 vs Intel HD Graphics 630 Comparison

Where Each One Wins

The benchmark data splits these two integrated and entry-level mobile graphics solutions along clear lines. The AMD Radeon R5 M320 takes the outright lead in both recorded head-to-head tests, but the Intel HD Graphics 630 counters with a different set of strengths that are not captured in direct comparison.

In the two shared workloads, the AMD Radeon R5 M320 wins both. The Geekbench OpenCL result shows the AMD part at 5051 points against 3587 for Intel, a 40.8% advantage. The Vulkan test narrows that gap but still favors AMD: 4262 versus 3540, a 20.4% lead. If a user's primary concern is raw compute throughput in these specific API workloads, the AMD solution is the clear pick.

However, the Intel HD Graphics 630 has its own win in a benchmark the AMD part does not appear in. The Intel GPU records a Geekbench Metal score of 5099, which is higher than either of the AMD scores in any test. This suggests that in Metal-based applications, the Intel part may offer competitive performance despite losing in the cross-platform OpenCL and Vulkan tests. The data does not include a Metal result for the AMD Radeon R5 M320, so direct comparison in that API is impossible.

The broader database averages reinforce this split. The AMD Radeon R5 M320 has an average benchmark score of 4657, placing it at the 27th percentile of all GPUs. The Intel HD Graphics 630 averages 4075, at the 24th percentile. The 582-point gap in average scores is meaningful, but the percentile difference is only 3 points, indicating both sit in the lower tier of the GPU landscape.

The rivalry data provides additional context. The AMD part's nearest rival is the AMD Radeon RX 9060 XT 16 GB with a 0% delta, meaning identical average scores. It also trades blows with the NVIDIA Quadro P400 (-0.6%), GeForce GTX 970M (+0.6%), and Quadro M3000M (+0.8%). The Intel part's nearest rivals include the AMD Radeon RX 9060 XT 8 GB (-0.4%), NVIDIA GeForce GT 755M (+1%), AMD FirePro M4150 (+1.5%), and NVIDIA Quadro K2100M (-1.8%). Both are clustered tightly with their peers, suggesting neither is an outlier in either direction.

Architecture Differences

The architectural divide between these two is substantial. The AMD Radeon R5 M320 uses the GCN 1.0 architecture on a chip codenamed Jet, manufactured on a 28 nm process at TSMC. It packs 690 million transistors into a 56 mm² die, yielding a transistor density of 12.3 million per square millimeter. The Intel HD Graphics 630 uses the Generation 9.5 architecture on a chip called Kaby Lake GT2, built on Intel's 14 nm++ process. The database records no transistor count or die size for the Intel part.

The compute resources differ markedly. AMD fields 320 shading units, 20 texture mapping units, and 8 raster operation units. Intel counters with 192 shading units, 24 TMUs, and only 3 ROPs. This configuration gives AMD a higher pixel rate at 6.840 GPixel/s versus Intel's 3.000 GPixel/s, but Intel wins on texture rate at 24.00 GTexel/s against AMD's 17.10 GTexel/s. The FP32 throughput favors AMD at 547.2 GFLOPS versus 384.0 GFLOPS. Intel does list an FP16 rate of 768.0 GFLOPS (2:1), while AMD has no recorded FP16 capability.

Memory architecture is another fundamental split. The AMD Radeon R5 M320 has dedicated 4 GB of DDR3 memory on a 64-bit bus, delivering 16.00 GB/s of bandwidth at a 1000 MHz memory clock (2 Gbps effective). The Intel HD Graphics 630 uses system shared memory for everything: size, type, bus width, and bandwidth are all listed as system dependent. This means the Intel part's memory performance varies with the host system's RAM configuration, while the AMD part has fixed, dedicated resources.

Clock behavior also diverges. AMD runs at a base of 780 MHz with a boost up to 855 MHz. Intel starts lower at 350 MHz base but boosts higher to 1000 MHz. The boost behavior suggests Intel's power management allows aggressive short-term clocking, while AMD's smaller clock range indicates a more conservative approach. The Intel part also has a recorded TDP of 15 W; the AMD part has no TDP listed.

API support shows Intel with a slight edge in version numbers. Both support DirectX 12 and OpenGL 4.6. Intel supports DirectX 12 (12_1) versus AMD's 12 (11_1), and Intel lists Vulkan 1.3 against AMD's 1.2.170. The Intel part also has a Metal benchmark score, indicating macOS compatibility, while AMD does not show a Metal result.

Head-to-Head Benchmarks

The recorded head-to-head data covers two tests, and the AMD Radeon R5 M320 wins both. The first is Geekbench OpenCL, where AMD scores 5051 against Intel's 3587. The 40.8% delta is the largest gap between the two in any shared test. This is a decisive margin, suggesting AMD's compute architecture handles OpenCL workloads substantially better despite the Intel part's higher boost clock.

The second test, Geekbench Vulkan, shows a narrower but still clear AMD victory. AMD scores 4262, Intel scores 3540, and the delta is 20.4%. The Vulkan gap is roughly half the OpenCL gap, indicating that Intel's newer API support (Vulkan 1.3 versus 1.2.170) may help close the distance in this workload. Still, AMD holds the lead.

The texture rate advantage for Intel (24.00 GTexel/s versus 17.10 GTexel/s) does not translate into a benchmark win in these tests. Similarly, Intel's higher boost clock of 1000 MHz versus AMD's 855 MHz does not overcome AMD's 128 additional shading units. The pixel rate difference is stark: AMD's 6.840 GPixel/s is more than double Intel's 3.000 GPixel/s, aligning with AMD's OpenCL dominance.

The average benchmark scores add context beyond the direct head-to-head. AMD's average of 4657 sits above Intel's 4075 by 14.3%. However, the Intel part's Metal score of 5099 exceeds AMD's best single score of 5051 in OpenCL. This suggests that in Metal-specific applications, the Intel part could potentially outperform the AMD part, even though no direct Metal comparison exists in the data.

The percentile rankings show both parts in the lower quartile of all GPUs. AMD at the 27th percentile and Intel at the 24th percentile means most discrete GPUs outperform both. The nearest rival data confirms this: AMD's closest competitor is the Radeon RX 9060 XT 16 GB at 0% delta, and Intel's is the Radeon RX 9060 XT 8 GB at -0.4%. These are not high-end parts by any measure.

The Verdict

From the recorded data, the AMD Radeon R5 M320 is the stronger performer in shared workloads. It wins both head-to-head tests, has a higher average benchmark score (4657 versus 4075), more shading units (320 versus 192), higher pixel rate (6.840 GPixel/s versus 3.000 GPixel/s), higher FP32 throughput (547.2 GFLOPS versus 384.0 GFLOPS), and dedicated 4 GB of VRAM with 16.00 GB/s bandwidth. The 40.8% OpenCL lead and 20.4% Vulkan lead are substantial margins.

The Intel HD Graphics 630 is not without merits. Its Metal score of 5099 is the single highest benchmark result between the two parts, and it offers higher texture rate (24.00 GTexel/s versus 17.10 GTexel/s), higher boost clock (1000 MHz versus 855 MHz), newer API versions (DirectX 12_1, Vulkan 1.3), and a lower TDP of 15 W. Its system shared memory means no dedicated VRAM allocation, which can be a benefit in memory-constrained systems but a drawback for consistent performance.

Users who prioritize compute performance in OpenCL or Vulkan workloads should choose the AMD Radeon R5 M320 based on the data. The margins are clear and consistent. Users whose applications rely on Metal, or who need the lower power envelope and newer API support, may find the Intel HD Graphics 630 more suitable. The Intel part's lack of a head-to-head Metal comparison leaves some uncertainty, but its 5099 Metal score is the highest recorded number for either GPU.

The percentile data suggests both parts are entry-level. Neither breaks the 30th percentile of all GPUs. For basic graphics acceleration, integrated display output, and light compute tasks, either will suffice. For anything demanding, the data indicates both will struggle.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The AMD Radeon R5 M320 scores 5051 against Intel's 3587, a 40.8% advantage for AMD.

Q: Does the Intel HD Graphics 630 win any benchmark?

A: Yes, the Intel part records a Geekbench Metal score of 5099, which is higher than any score the AMD Radeon R5 M320 achieves in its recorded tests.

Q: What is the difference in average benchmark scores?

A: The AMD Radeon R5 M320 averages 4657, while the Intel HD Graphics 630 averages 4075, a gap of 582 points.

Q: How much VRAM does each GPU have?

A: The AMD Radeon R5 M320 has 4 GB of dedicated DDR3 memory. The Intel HD Graphics 630 uses system shared memory with no dedicated VRAM.

Q: Which GPU has more shading units?

A: The AMD Radeon R5 M320 has 320 shading units, while the Intel HD Graphics 630 has 192.

Q: What is the Vulkan score difference?

A: AMD scores 4262 and Intel scores 3540, giving AMD a 20.4% lead in the Geekbench Vulkan test.

Specification Differences

| Specification | AMD Radeon R5 M320 | Intel HD Graphics 630 |

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

| Architecture | GCN 1.0 | Generation 9.5 |

| Process Node | 28 nm | 14 nm++ |

| Foundry | TSMC | Intel |

| Transistors | 690 million | Not recorded |

| Die Size | 56 mm² | Not recorded |

| Base Clock | 780 MHz | 350 MHz |

| Boost Clock | 855 MHz | 1000 MHz |

| Memory Size | 4 GB | System Shared |

| Memory Type | DDR3 | System Shared |

| Memory Bus Width | 64 bit | System Shared |

| Memory Bandwidth | 16.00 GB/s | System Dependent |

| Shading Units | 320 | 192 |

| TMUs | 20 | 24 |

| ROPs | 8 | 3 |

| Pixel Rate | 6.840 GPixel/s | 3.000 GPixel/s |

| Texture Rate | 17.10 GTexel/s | 24.00 GTexel/s |

| FP32 | 547.2 GFLOPS | 384.0 GFLOPS |

| FP16 | Not recorded | 768.0 GFLOPS (2:1) |

| TDP | Not recorded | 15 W |

| Bus Interface | PCIe 3.0 x8 | Ring Bus |

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

| Vulkan | 1.2.170 | 1.3 |

| Release Date | 2015-05-04 | 2016-08-29 |

| Average Benchmark Score | 4657 | 4075 |

| Percentile vs All GPUs | 27 | 24 |