AMD Radeon HD 8690M vs Intel UHD Graphics 750 Comparison

Head-to-Head Benchmarks

The only direct benchmark comparison available in the database is Geekbench OpenCL, and the result is clear: Intel UHD Graphics 750 wins outright with a score of 6743 against AMD Radeon HD 8690M's 6137, a 9.9% advantage. This is a meaningful gap in raw compute workloads, placing the Intel part ahead in any OpenCL-based task, from media processing to general-purpose GPU compute.

Looking at the broader database context, the Intel UHD Graphics 750 posts an average benchmark score of 7441 across all recorded tests, which places it in the 40th percentile of all GPUs. The AMD Radeon HD 8690M, by contrast, has an average score of 6137 and sits in the 36th percentile. That percentile difference, while modest, reinforces the same conclusion: the Intel integrated solution is the stronger performer in the database's aggregate measurements.

The AMD GPU's nearest rivals in the database include the Intel Iris Pro Graphics 6200 (average score 6117, 0.3% behind) and the NVIDIA GeForce MX230 (average score 6077, 1% behind). The Intel UHD Graphics 750's nearest rivals include the AMD Radeon HD 8850M (average score 7447, just 0.1% ahead) and the NVIDIA GeForce GTX 1650 (average score 7472, 0.4% ahead). This shows the Intel part is competitive with much more recent discrete graphics solutions, even though it is an integrated GPU. The AMD Radeon HD 8690M, meanwhile, is effectively matched with a 2015-era integrated Iris Pro part, which speaks to its age and limited performance ceiling.

In the head-to-head comparison, Intel wins the single recorded test, giving it a 1-0 record in the database. The delta of 9.9% is not a narrow margin; it is a decisive lead in a compute benchmark that stresses raw shader throughput and memory access patterns. For any workload that relies on OpenCL acceleration, the data points to the Intel UHD Graphics 750 as the better choice.

Architecture Differences

The two GPUs come from different architectural generations and entirely different design philosophies. The Intel UHD Graphics 750 is built on Intel's Generation 12.1 architecture, part of the Rocket Lake platform, and it uses Intel's 14 nm+++ process node, fabricated in-house by Intel. The AMD Radeon HD 8690M, on the other hand, uses the GCN 1.0 architecture, specifically the Sun chip, and is manufactured by TSMC on a 28 nm process. The process node difference is significant: 14 nm+++ vs 28 nm, which gives Intel a density and efficiency advantage on paper.

The AMD chip does have a documented transistor count of 690 million on a 56 mm² die, yielding a transistor density of 12.3M per mm². The Intel part has no transistor or die size data recorded in the database, so a direct density comparison is not possible. However, the architectural generation gap is clear: GCN 1.0 dates back to 2013, while Intel's Generation 12.1 is from 2021.

Shader resources differ notably. The AMD Radeon HD 8690M has 320 shading units and 20 texture mapping units, while the Intel UHD Graphics 750 has 256 shading units and 16 TMUs. Both have 8 ROPs. This means AMD has a 25% advantage in shader count and a 25% advantage in TMU count, yet it still loses in OpenCL performance. That outcome suggests the Intel architecture extracts more useful work per shader, or that memory and driver overhead play a larger role than raw unit counts.

Memory configurations are completely different. The Intel UHD Graphics 750 uses system shared memory, with system-dependent bandwidth and no dedicated VRAM. The AMD Radeon HD 8690M has 2 GB of dedicated GDDR5 memory on a 64-bit bus, with 32.00 GB/s of bandwidth and a 1000 MHz memory clock (4 Gbps effective). Dedicated VRAM is typically a major advantage for discrete GPUs, yet the Intel part still wins the compute benchmark, which indicates that its memory architecture, likely benefiting from modern system memory and cache design, is sufficient to overcome the lack of dedicated VRAM in this test.

Clock speeds also favor AMD. The Radeon HD 8690M runs at a base clock of 925 MHz and a boost clock of 975 MHz. The Intel UHD Graphics 750 runs at a base of 300 MHz and a boost of 1300 MHz. The AMD part has a much higher base clock, but Intel's boost clock is substantially higher. Peak pixel and texture rates reflect this: Intel posts 10.40 GPixel/s and 20.80 GTexel/s, while AMD posts 7.800 GPixel/s and 19.50 GTexel/s. Intel wins both, despite fewer TMUs and ROPs, thanks to its higher boost clock and architectural efficiency.

API support differs as well. The Intel part supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The AMD part supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Intel has a newer DirectX feature level and a newer Vulkan version, which matters for modern game and application compatibility.

The bus interface also differs: Intel uses a Ring Bus, typical for integrated GPUs, while AMD uses PCIe 3.0 x8, typical for discrete mobile GPUs. The Intel part is integrated (IGP slot width), while the AMD part is a discrete mobile chip. Power consumption data is only recorded for Intel at 15 W; AMD's TDP is not listed in the database.

The release dates are far apart: Intel launched on 2021-03-29, AMD on 2013-02-28. Both are end-of-life products. AMD's predecessor is listed as London and its successor as Gem System, while Intel has no predecessor or successor recorded.

The Verdict

The data is unambiguous: the Intel UHD Graphics 750 is the faster GPU. It wins the only direct benchmark in the database, and it holds a higher average benchmark score and a higher percentile ranking. The 9.9% OpenCL lead is the headline number, and it holds up under scrutiny given the Intel part's superior pixel rate, texture rate, and FP32 throughput of 665.6 GFLOPS versus AMD's 624.0 GFLOPS.

The AMD Radeon HD 8690M does have advantages in memory: 2 GB of dedicated GDDR5 with 32.00 GB/s bandwidth versus Intel's system-shared memory. It also has more shading units (320 vs 256) and more TMUs (20 vs 16). But these advantages do not translate into benchmark wins. The recorded data shows that raw resource counts are not enough to overcome the architectural and generational gap.

Pick the Intel UHD Graphics 750 if you need better compute performance, newer API support (DirectX 12_1 vs 11_1, Vulkan 1.4 vs 1.2.170), and a more modern architecture. The 40th percentile ranking versus the 36th percentile ranking confirms it is the better-positioned GPU in the database's overall distribution.

Pick the AMD Radeon HD 8690M only if the workload specifically requires dedicated VRAM, or if the system cannot provide adequate shared memory bandwidth. In that narrow scenario, the 2 GB GDDR5 configuration is the only clear advantage. Otherwise, the Intel part wins on performance, API modernity, and efficiency.

Specification Differences

The following specifications differ between the two GPUs:

• Process Node: Intel 14 nm+++ vs AMD 28 nm
• Foundry: Intel vs TSMC
• Transistors: Not recorded vs 690 million
• Die Size: Not recorded vs 56 mm²
• Transistor Density: Not recorded vs 12.3M / mm²
• Base Clock: 300 MHz vs 925 MHz
• Boost Clock: 1300 MHz vs 975 MHz
• Memory Size: System Shared vs 2 GB
• Memory Type: System Shared vs GDDR5
• Memory Bus Width: System Shared vs 64 bit
• Memory Bandwidth: System Dependent vs 32.00 GB/s
• Memory Clock: Not applicable vs 1000 MHz (4 Gbps effective)
• Shading Units: 256 vs 320
• TMUs: 16 vs 20
• Pixel Rate: 10.40 GPixel/s vs 7.800 GPixel/s
• Texture Rate: 20.80 GTexel/s vs 19.50 GTexel/s
• FP32: 665.6 GFLOPS vs 624.0 GFLOPS
• FP16: 1,331.2 GFLOPS (2:1) vs not recorded
• TDP: 15 W vs not recorded
• Slot Width: IGP vs not recorded
• Bus Interface: Ring Bus vs PCIe 3.0 x8
• Display Outputs: Motherboard Dependent vs not recorded
• DirectX Support: 12 (12_1) vs 12 (11_1)
• Vulkan Support: 1.4 vs 1.2.170
• Release Date: 2021-03-29 vs 2013-02-28
• Predecessor: Not recorded vs London
• Successor: Not recorded vs Gem System

FAQ

Q: Which GPU is faster in OpenCL benchmarks?

A: The Intel UHD Graphics 750 wins the Geekbench OpenCL test with a score of 6743 against the AMD Radeon HD 8690M's 6137, a 9.9% advantage.

Q: How do their overall benchmark scores compare?

A: The Intel UHD Graphics 750 has an average benchmark score of 7441 and ranks in the 40th percentile of all GPUs. The AMD Radeon HD 8690M has an average score of 6137 and ranks in the 36th percentile.

Q: Does the AMD GPU have more shading units?

A: Yes, the AMD Radeon HD 8690M has 320 shading units and 20 TMUs, while the Intel UHD Graphics 750 has 256 shading units and 16 TMUs. Both have 8 ROPs.

Q: Which GPU has dedicated VRAM?

A: The AMD Radeon HD 8690M has 2 GB of dedicated GDDR5 memory on a 64-bit bus with 32.00 GB/s bandwidth. The Intel UHD Graphics 750 uses system shared memory with system-dependent bandwidth.

Q: Which GPU supports newer APIs?

A: The Intel UHD Graphics 750 supports DirectX 12 (12_1) and Vulkan 1.4, while the AMD Radeon HD 8690M supports DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6.

Q: Are these GPUs still in production?

A: No, both are end-of-life products. The Intel UHD Graphics 750 was released on 2021-03-29, and the AMD Radeon HD 8690M was released on 2013-02-28.

Where Each One Wins

The Intel UHD Graphics 750 wins in raw compute performance. The 9.9% OpenCL lead is the strongest evidence, supported by higher pixel rate (10.40 vs 7.800 GPixel/s), higher texture rate (20.80 vs 19.50 GTexel/s), and higher FP32 throughput (665.6 vs 624.0 GFLOPS). It also wins on API support, with DirectX 12_1 and Vulkan 1.4 versus the AMD part's DirectX 12_1 and Vulkan 1.2.170. For any modern workload that leverages OpenCL, Vulkan, or modern DirectX features, the Intel part is the safer pick. Its 40th percentile ranking versus the AMD part's 36th percentile also indicates better overall performance in the database's full GPU distribution.

The AMD Radeon HD 8690M wins in memory configuration. The 2 GB of dedicated GDDR5 VRAM with 32.00 GB/s bandwidth is a clear advantage over system shared memory, especially in systems where system memory bandwidth is limited. It also has more shading units (320 vs 256) and more TMUs (20 vs 16), which could matter in workloads that scale directly with those resources, even if the recorded benchmarks do not reflect it. Its higher base clock of 925 MHz versus Intel's 300 MHz could also provide more consistent performance in sustained workloads that do not allow Intel's boost clock to stay at 1300 MHz.

However, the AMD part's wins are theoretical and resource-based, while the Intel part's wins are measured. The database records one benchmark, and Intel wins it. The AMD Radeon HD 8690M's nearest rivals include the Intel Iris Pro Graphics 6200 (0.3% behind), meaning it is barely ahead of a 2015 integrated GPU. The Intel UHD Graphics 750's nearest rivals include the NVIDIA GeForce GTX 1650 (0.4% behind, a much more recent discrete GPU). This comparison illustrates just how far the Intel part has moved the performance needle relative to its era. The AMD Radeon HD 8690M is a competent legacy GPU, and the Intel UHD Graphics 750 is a modern integrated GPU that outclasses it in every recorded benchmark.