AMD Radeon HD 8690M vs Intel UHD Graphics P630 Comparison

The Verdict

The recorded data positions the AMD Radeon HD 8690M ahead of the Intel UHD Graphics P630 in the only shared benchmark test. In Geekbench OpenCL, the AMD part scores 6137, which is 20.1% higher than the Intel part's 5111. The AMD GPU also sits at the 36th percentile among all GPUs in the database, while the Intel UHD Graphics P630 lands at the 31st percentile. The AMD Radeon HD 8690M wins the sole head-to-head benchmark, taking 1 win to 0.

The Intel UHD Graphics P630, however, is not without justification. It is an integrated processor graphics solution with a 15 W TDP and a Ring Bus interface, making it suitable for systems where the CPU and GPU share the same package. The AMD Radeon HD 8690M, by contrast, is a discrete mobile GPU with its own 2 GB of GDDR5 memory on a 64-bit bus, delivering 32.00 GB/s of bandwidth. The data suggests the AMD part is the stronger performer for tasks that rely on raw OpenCL compute, while the Intel part is the only option when a separate graphics card is not feasible.

Buyers should pick the AMD Radeon HD 8690M if they need the higher compute throughput and have access to a discrete GPU slot. The Intel UHD Graphics P630 should be selected when the system must rely on integrated graphics, given its lower power envelope and shared memory architecture. The benchmark results show a clear performance gap, but the Intel part's integration is a structural advantage that no discrete card can match.

Architecture Differences

The two GPUs come from different architectural lineages. The AMD Radeon HD 8690M uses the GCN 1.0 architecture, built on a 28 nm process at TSMC. Its chip is codenamed Sun, and it belongs to the Solar System generation of the HD 8600M series. The GPU contains 690 million transistors on a 56 mm² die, giving it a transistor density of 12.3 million transistors per mm². Its predecessor is London, and its successor is Gem System. The production status is listed as end-of-life, with a release date of February 28, 2013.

The Intel UHD Graphics P630 uses the Generation 9.5 architecture, built on Intel's 14 nm+++ process. Its chip is codenamed Comet Lake GT2, and it belongs to the HD Graphics-W generation for Comet Lake processors. The data does not list transistor count, die size, or transistor density for this part. The production status is end-of-life, with a release date of May 12, 2020. No predecessor or successor is recorded.

The AMD part has 320 shading units, 20 texture mapping units, and 8 raster operation units. The Intel part has 192 shading units, 24 texture mapping units, and only 3 raster operation units. The AMD GPU's pixel rate is 7.800 GPixel/s, while the Intel GPU's is 3.600 GPixel/s. The texture rates tell a different story: the AMD part achieves 19.50 GTexel/s, while the Intel part reaches 28.80 GTexel/s. The AMD GPU delivers 624.0 GFLOPS of FP32 compute, and the Intel GPU delivers 460.8 GFLOPS of FP32. The Intel part also lists FP16 performance of 921.6 GFLOPS (2:1), while the AMD part has no recorded FP16 figure.

The AMD Radeon HD 8690M connects via PCIe 3.0 x8, while the Intel UHD Graphics P630 uses a Ring Bus interface. The AMD part has no recorded TDP, whereas the Intel part is rated at 15 W and is classified as an IGP. The Intel GPU's display outputs are motherboard dependent, and its memory bandwidth is system dependent. The AMD part uses 2 GB of GDDR5 memory, while the Intel part uses system shared memory.

Head-to-Head Benchmarks

The database contains one head-to-head benchmark between these two GPUs: Geekbench OpenCL. The AMD Radeon HD 8690M scores 6137, and the Intel UHD Graphics P630 scores 5111. This gives the AMD part a 20.1% advantage. That is the largest winning margin recorded in the head-to-head data.

Looking at the AMD part's nearest rivals provides context. The AMD Radeon HD 8690M scores 0.3% higher than the Intel Iris Pro Graphics 6200, which averages 6117. It is 1% ahead of the NVIDIA RTX A400 (6078) and 1% ahead of the NVIDIA GeForce MX230 (6077). It trails the AMD Radeon HD 6950 by 1.2%, which averages 6210. The AMD part's 6137 score places it just above a cluster of competitors in the 6077 to 6117 range.

The Intel UHD Graphics P630's nearest rivals show a similar clustering. Its average benchmark score is 5370, which is 0.2% ahead of the AMD Radeon R7 M445 (5358) and 0.9% ahead of the NVIDIA GeForce 840M (5322). It is 1% ahead of the NVIDIA GeForce 930A (5317). It trails the AMD Radeon R7 M365X by 0.8%, which averages 5416. The Intel part's own Geekbench Vulkan score is 5628, which is higher than its OpenCL score of 5111.

The data shows that the AMD Radeon HD 8690M sits in a performance tier roughly 600 to 700 points above the Intel UHD Graphics P630 in OpenCL. The 20.1% delta in the head-to-head test is substantial, and the nearest rival comparisons confirm that the AMD part competes with slightly older discrete GPUs, while the Intel part competes with low-end discrete parts from several generations ago.

Specification Differences

The two parts differ in several key specification fields. The process node is 28 nm for the AMD part versus 14 nm+++ for the Intel part. The foundry is TSMC for AMD versus Intel for the Intel part. The AMD GPU has 690 million transistors, while the Intel part has no recorded transistor count. The AMD die size is 56 mm², and the Intel die size is not recorded.

The base clock differs significantly: 925 MHz for the AMD part versus 350 MHz for the Intel part. The boost clock is 975 MHz for the AMD part versus 1200 MHz for the Intel part. The AMD memory clock is 1000 MHz with 4 Gbps effective, while the Intel part uses system shared memory with a system dependent bandwidth.

The memory configuration is a major split. The AMD Radeon HD 8690M has 2 GB of GDDR5 memory on a 64-bit bus, delivering 32.00 GB/s. The Intel UHD Graphics P630 has system shared memory with a system dependent bandwidth. The AMD part has 320 shading units, 20 TMUs, and 8 ROPs. The Intel part has 192 shading units, 24 TMUs, and 3 ROPs.

The pixel rate is 7.800 GPixel/s for the AMD part versus 3.600 GPixel/s for the Intel part. The texture rate is 19.50 GTexel/s for the AMD part versus 28.80 GTexel/s for the Intel part. The FP32 compute is 624.0 GFLOPS for the AMD part versus 460.8 GFLOPS for the Intel part. The Intel part adds FP16 compute of 921.6 GFLOPS (2:1), while the AMD part has no FP16 listing.

The TDP is not recorded for the AMD part, while the Intel part is rated at 15 W. The slot width is not recorded for the AMD part, while the Intel part is listed as an IGP. The bus interface is PCIe 3.0 x8 for the AMD part versus Ring Bus for the Intel part. The display outputs are not recorded for the AMD part, while the Intel part is motherboard dependent. The AMD part supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The Intel part supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The AMD Radeon HD 8690M scores 6137, which is 20.1% higher than the Intel UHD Graphics P630's 5111.

Q: What is the memory configuration of each GPU?

A: The AMD Radeon HD 8690M has 2 GB of GDDR5 memory on a 64-bit bus with 32.00 GB/s bandwidth. The Intel UHD Graphics P630 uses system shared memory with system dependent bandwidth.

Q: How do their shading unit counts compare?

A: The AMD Radeon HD 8690M has 320 shading units, while the Intel UHD Graphics P630 has 192 shading units.

Q: Which GPU has the higher texture rate?

A: The Intel UHD Graphics P630 has a texture rate of 28.80 GTexel/s, which is higher than the AMD Radeon HD 8690M's 19.50 GTexel/s.

Q: What is the power consumption of the Intel UHD Graphics P630?

A: The Intel UHD Graphics P630 is rated at 15 W and is classified as an IGP. The AMD Radeon HD 8690M has no recorded TDP.

Q: How do the two GPUs compare in terms of API support?

A: The AMD Radeon HD 8690M supports DirectX 12 (11_1) and Vulkan 1.2.170. The Intel UHD Graphics P630 supports DirectX 12 (12_1) and Vulkan 1.3. Both support OpenGL 4.6.

Where Each One Wins

The AMD Radeon HD 8690M wins in raw compute throughput. Its Geekbench OpenCL score of 6137 beats the Intel part by 20.1%, and its FP32 compute of 624.0 GFLOPS is higher than the Intel part's 460.8 GFLOPS. It also has a higher pixel rate (7.800 GPixel/s versus 3.600 GPixel/s) and more shading units (320 versus 192). The AMD part's dedicated 2 GB of GDDR5 memory with 32.00 GB/s bandwidth gives it a clear advantage for workloads that need fast, dedicated memory access. Its nearest rivals include the Intel Iris Pro Graphics 6200, NVIDIA RTX A400, and NVIDIA GeForce MX230, and it sits just 1.2% behind the AMD Radeon HD 6950.

The Intel UHD Graphics P630 wins in integration and specific throughput metrics. Its 15 W TDP makes it suitable for power-constrained systems, and its IGP classification means it does not require a separate graphics card. It has a higher texture rate (28.80 GTexel/s versus 19.50 GTexel/s) and more TMUs (24 versus 20). Its FP16 compute of 921.6 GFLOPS (2:1) is a feature the AMD part lacks. It also supports Vulkan 1.3, a newer version than the AMD part's Vulkan 1.2.170. Its nearest rivals are the AMD Radeon R7 M445, AMD Radeon R7 M365X, NVIDIA GeForce 840M, and NVIDIA GeForce 930A, all of which it matches within 1%.

For use-case splitting, the AMD Radeon HD 8690M is the choice for OpenCL compute tasks, pixel-heavy rendering, and any workload that benefits from dedicated GDDR5 memory. The Intel UHD Graphics P630 is the choice for integrated systems where power draw is a concern and where texture throughput matters more than pixel rate. The database records only one head-to-head test, and the AMD part won it, but the Intel part's integration advantages are structural and cannot be captured in a single benchmark score.