AMD Radeon HD 8690M vs Intel Iris Pro Graphics P6300 Comparison

Where Each One Wins

The recorded benchmark data contains a single head-to-head comparison: Geekbench OpenCL. In that test, the AMD Radeon HD 8690M wins outright, scoring 6137 against the Intel Iris Pro Graphics P6300's 5712, a 7.4% advantage. That makes the AMD part the clear choice for any workload that leans on OpenCL compute performance, which typically includes general-purpose GPU tasks such as image processing, video encoding acceleration, and scientific or financial simulations that can be offloaded to the graphics processor.

The Intel Iris Pro Graphics P6300, by contrast, does not win the single measured head-to-head test. However, the data shows that its strengths lie elsewhere. As an integrated part of a Broadwell processor, it draws only 15 W according to the TDP field, and it uses System Shared memory, meaning it has no dedicated VRAM of its own. That configuration is typical of a mobile or low-power platform where the GPU shares the system memory pool. The AMD Radeon HD 8690M, with its dedicated 2 GB of GDDR5 memory on a 64-bit bus delivering 32.00 GB/s of bandwidth, is built for discrete graphics duty. So while the AMD part wins the compute benchmark, the Intel part wins on integration and power envelope, a trade-off that matters in thin-and-light laptops where a separate GPU is not an option.

In terms of database-wide percentile ranking, the AMD Radeon HD 8690M sits at the 36th percentile of all GPUs, while the Intel Iris Pro Graphics P6300 sits at the 33rd percentile. That three-point percentile gap reinforces the head-to-head result: the AMD part is positioned slightly higher in the overall performance distribution. The nearest rival data also frames the two parts differently. The AMD Radeon HD 8690M's closest competitors include the Intel Iris Pro Graphics 6200 (0.3% ahead), the NVIDIA RTX A400 (1% ahead), the NVIDIA GeForce MX230 (1% ahead), and the AMD Radeon HD 6950 (1.2% behind). The Intel Iris Pro Graphics P6300's nearest rivals are the NVIDIA GeForce GTX 670MX (0.1% behind), the NVIDIA GeForce GTX 550 Ti (0.3% behind), the AMD Radeon HD 8790M (0.4% ahead), and the NVIDIA Quadro M500M (1.9% ahead). These clusters show that both parts operate in a similar performance tier, but the AMD part has a slight edge in the measured test.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The AMD Radeon HD 8690M uses the Sun chip built on the GCN 1.0 architecture, manufactured by TSMC on a 28 nm process. It packs 690 million transistors into a 56 mm² die, yielding a transistor density of 12.3 million transistors per square millimeter. The Intel Iris Pro Graphics P6300 uses the Broadwell GT3e chip, built on Intel's Generation 8.0 architecture, manufactured by Intel on a 14 nm process. The database does not list transistor count, die size, or transistor density for the Intel part, so no direct comparison is possible on those metrics. The process node difference is clear, though: 28 nm for AMD versus 14 nm for Intel, a generation gap that gives Intel a theoretical density advantage, though the AMD part's dedicated memory and higher clocks compensate in practice.

Clock speeds differ dramatically. The AMD Radeon HD 8690M has a base clock of 925 MHz and a boost clock of 975 MHz, with memory clocked at 1000 MHz, which translates to 4 Gbps effective for its GDDR5 memory. The Intel Iris Pro Graphics P6300 has a much lower base clock of 300 MHz and a boost clock of 800 MHz, with system shared memory whose bandwidth is listed as System Dependent. That clock disparity is the primary reason the AMD part wins the compute benchmark despite having fewer shading units. The AMD part has 320 shading units, 20 texture mapping units, and 8 render output units. The Intel part has 384 shading units, 48 texture mapping units, and only 6 render output units. So Intel has more shaders and far more texture units, but the AMD part's higher clocks and dedicated memory allow it to pull ahead in the measured test.

Pixel and texture rates reflect these architectural choices. The AMD Radeon HD 8690M achieves 7.800 GPixel/s pixel rate and 19.50 GTexel/s texture rate. The Intel Iris Pro Graphics P6300 achieves 4.800 GPixel/s pixel rate, which is lower, but its texture rate is 38.40 GTexel/s, which is nearly double the AMD part's texture throughput. That is a direct result of the Intel part having 48 TMUs against the AMD part's 20. In texture-heavy workloads, the Intel part could theoretically have an advantage, but the single benchmark in the database does not isolate texture performance.

FP32 compute also tells a nuanced story. The AMD Radeon HD 8690M delivers 624.0 GFLOPS, while the Intel Iris Pro Graphics P6300 delivers 614.4 GFLOPS. The difference is only 1.6%, yet the recorded OpenCL benchmark shows a 7.4% gap in favor of AMD. That suggests the AMD part extracts more real-world performance from its compute capability, likely due to its dedicated memory and higher clock consistency. Neither part supports FP16 according to the database, so half-precision compute is not a differentiator.

Memory architecture is the starkest contrast. The AMD Radeon HD 8690M has 2 GB of GDDR5 on a 64-bit bus with 32.00 GB/s bandwidth. The Intel Iris Pro Graphics P6300 uses System Shared memory, with System Shared type, System Shared bus width, and System Dependent bandwidth. This means the Intel part's memory performance is entirely dependent on the host system's RAM configuration, which is not fixed in the database. For any workload that is memory-bandwidth sensitive, the AMD part's dedicated 32.00 GB/s is a concrete advantage.

API support differs as well. Both parts support DirectX 12 (11_1), so they are on par for modern DirectX titles. For OpenGL, the AMD Radeon HD 8690M supports version 4.6, while the Intel Iris Pro Graphics P6300 supports version 4.4. For Vulkan, the AMD part supports version 1.2.170, while the Intel part supports only version 1.0. That gives the AMD part a clear software compatibility edge for newer Vulkan applications and newer OpenGL titles. The Intel part's bus interface is listed as Ring Bus, reflecting its integration into the CPU package, while the AMD part uses PCIe 3.0 x8. Display outputs for the Intel part are Motherboard Dependent, while the AMD part's display outputs are not listed in the database.

Head-to-Head Benchmarks

The only head-to-head benchmark recorded is Geekbench OpenCL. The AMD Radeon HD 8690M scores 6137, and the Intel Iris Pro Graphics P6300 scores 5712. The delta is 7.4% in favor of AMD. This is a decisive, if modest, win. For context, the AMD part's nearest rival, the Intel Iris Pro Graphics 6200, scores 6117, which is 0.3% behind the AMD part. The NVIDIA RTX A400 scores 6078, 1% behind. The NVIDIA GeForce MX230 scores 6077, also 1% behind. The AMD Radeon HD 6950 scores 6210, which is 1.2% ahead. So the AMD Radeon HD 8690M sits in a tight cluster where the spread from the top to the bottom of its nearest rivals is only about 2.2%.

The Intel Iris Pro Graphics P6300, meanwhile, sits in a slightly lower cluster. Its nearest rival, the NVIDIA GeForce GTX 670MX, scores 5721, which is 0.1% ahead of the Intel part. The NVIDIA GeForce GTX 550 Ti scores 5731, 0.3% ahead. The AMD Radeon HD 8790M scores 5691, 0.4% behind. The NVIDIA Quadro M500M scores 5604, 1.9% behind. The Intel part's cluster is tighter, with a spread of only about 2.2% from the lowest to the highest rival, but the entire cluster sits roughly 400 to 450 points below the AMD part's cluster.

The 7.4% delta between the two reviewed parts is larger than the gap between either part and its own nearest rivals. That means the AMD Radeon HD 8690M does not just edge out the Intel Iris Pro Graphics P6300 by a rounding error; it holds a clear, repeatable advantage in the measured OpenCL workload. The AMD part's higher FP32 rating (624.0 GFLOPS vs 614.4 GFLOPS) and its dedicated memory bandwidth (32.00 GB/s vs System Dependent) both contribute to this result.

It is importantly the Intel part's texture rate of 38.40 GTexel/s is nearly double the AMD part's 19.50 GTexel/s, and its pixel rate of 4.800 GPixel/s is lower than the AMD part's 7.800 GPixel/s. The database does not include a synthetic texture benchmark, so these theoretical rates remain untested in the recorded measurements. The single benchmark available favors the AMD part, and the percentile data agrees: 36th percentile for AMD versus 33rd percentile for Intel.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The AMD Radeon HD 8690M scores 6137, while the Intel Iris Pro Graphics P6300 scores 5712. The AMD part leads by 7.4%.

Q: How do these GPUs compare to their nearest rivals?

A: The AMD Radeon HD 8690M is 0.3% behind the Intel Iris Pro Graphics 6200, 1% behind both the NVIDIA RTX A400 and the NVIDIA GeForce MX230, and 1.2% ahead of the AMD Radeon HD 6950. The Intel Iris Pro Graphics P6300 is 0.1% behind the NVIDIA GeForce GTX 670MX, 0.3% behind the NVIDIA GeForce GTX 550 Ti, 0.4% ahead of the AMD Radeon HD 8790M, and 1.9% ahead of the NVIDIA Quadro M500M.

Q: What are the memory configurations of these two GPUs?

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 Iris Pro Graphics P6300 uses System Shared memory with System Dependent bandwidth.

Q: Which GPU has more shading units?

A: The Intel Iris Pro Graphics P6300 has 384 shading units, while the AMD Radeon HD 8690M has 320 shading units. Despite having fewer shading units, the AMD part scores higher in the measured OpenCL benchmark.

Q: What is the power consumption difference?

A: The Intel Iris Pro Graphics P6300 has a listed TDP of 15 W. The AMD Radeon HD 8690M does not have a TDP listed in the database.

Q: Which GPU supports newer graphics APIs?

A: The AMD Radeon HD 8690M supports OpenGL 4.6 and Vulkan 1.2.170. The Intel Iris Pro Graphics P6300 supports OpenGL 4.4 and Vulkan 1.0. Both support DirectX 12 (11_1).

The Verdict

The data points to a clear but narrow victory for the AMD Radeon HD 8690M in raw compute performance. Its Geekbench OpenCL score of 6137 beats the Intel Iris Pro Graphics P6300's 5712 by 7.4%, and its 36th percentile ranking sits above the Intel part's 33rd percentile. The AMD part also brings dedicated 2 GB GDDR5 memory with 32.00 GB/s bandwidth, which removes the variable of system memory performance from the equation. For users who need consistent OpenCL compute performance in a discrete GPU form factor, the AMD Radeon HD 8690M is the stronger choice according to the recorded measurements.

The Intel Iris Pro Graphics P6300, however, has its own rationale. Its 15 W TDP and integrated nature make it suitable for low-power platforms where a discrete GPU is not feasible. Its 384 shading units and 48 texture mapping units give it a theoretical edge in texture throughput (38.40 GTexel/s vs 19.50 GTexel/s), even though that advantage does not show up in the single benchmark recorded. Its System Shared memory eliminates the cost and complexity of dedicated VRAM, and its Ring Bus interface reflects its tight integration with the Broadwell CPU. For a system builder prioritizing power efficiency and integration over compute headroom, the Intel part is defensible.

The AMD Radeon HD 8690M is the pick when the workload is known to use OpenCL and when dedicated memory bandwidth matters. The Intel Iris Pro Graphics P6300 is the pick when the platform requires a 15 W integrated solution and when texture throughput is more important than compute throughput. The benchmark data favors AMD, but the architectural profiles show that each part serves a different use case. The AMD part wins the measured test; the Intel part wins on power and integration. Both parts are end-of-life, so the choice is relevant only for existing platforms or legacy upgrades. Within that context, the recorded data says the AMD Radeon HD 8690M delivers more compute per benchmark point, while the Intel Iris Pro Graphics P6300 delivers a lower-power integrated alternative with double the texture rate.