AMD Radeon HD 8790M vs AMD Radeon R7 M460 Comparison

Head-to-Head Benchmarks

The database contains a single direct comparison between these two mobile graphics processors, and it is a decisive one. In the Geekbench OpenCL test, the AMD Radeon R7 M460 scores 6612 points against 5017 points for the AMD Radeon HD 8790M. That translates to a 31.8% advantage for the newer part, a substantial gap that places the two chips in different performance tiers despite their shared architectural lineage.

The R7 M460’s victory is not a narrow margin. A 31.8% delta in compute workloads is significant enough to be felt in real-world tasks such as GPU-accelerated video encoding, OpenCL-based rendering, or any productivity application that offloads parallel math to the graphics processor. The HD 8790M, while competitive in its own era, simply cannot keep pace with the raw throughput of its successor.

Looking at the broader context, the R7 M460 sits at the 38th percentile of all GPUs in the database, while the HD 8790M rests at the 33rd percentile. That five-point gap in percentile ranking confirms that the M460 is not merely faster than its predecessor in a vacuum, but that it also holds a better position relative to the entire field of recorded graphics hardware. The average benchmark score for the M460 is 6612, matching its single OpenCL result, whereas the HD 8790M averages 5691 across its two recorded tests (5017 in OpenCL and 6365 in Vulkan). Even when accounting for the HD 8790M’s stronger Vulkan showing, its average remains roughly 14% below the M460’s OpenCL score.

The nearest rivals for each card further illustrate the competitive landscape. The R7 M460’s closest competitors include the AMD Radeon HD 7730M (6581, a 0.5% gap), the Intel UHD Graphics P750 (6554, a 0.9% gap), and the NVIDIA GeForce GT 1010 (6698, where the M460 trails by 1.3%). The M460 also edges out the NVIDIA GeForce GTX 670M (6513) by 1.5%. These tight margins indicate that the M460 lands in a crowded mid-range segment where small percentage differences separate rivals.

The HD 8790M’s nearest rivals paint a similar picture of a card holding its own against contemporaries but with less headroom. It trails the Intel Iris Pro Graphics P6300 by 0.4%, the NVIDIA GeForce GTX 670MX by 0.5%, and the NVIDIA GeForce GTX 550 Ti by 0.7%, while leading the NVIDIA Quadro M500M by 1.6%. These sub-2% deltas show that the HD 8790M is competitive within its immediate peer group, but that group sits at a lower absolute performance level than the M460’s circle.

The Verdict

The data points to a clear hierarchy: the AMD Radeon R7 M460 is the faster GPU in head-to-head compute testing. Its 31.8% lead in OpenCL over the HD 8790M is the single most important number in this comparison. For any user prioritizing raw compute throughput in a mobile workstation or gaming laptop, the M460 is the logical choice.

The HD 8790M, however, should not be dismissed outright. Its Vulkan score of 6365 is notably higher than its OpenCL score of 5017, suggesting that it handles the Vulkan API more efficiently. In the database, the HD 8790M’s Vulkan result is actually close to the M460’s OpenCL score (6365 versus 6612, a difference of only 3.7%). This indicates that if a workload relies on Vulkan rather than OpenCL, the performance gap between these two cards narrows considerably.

The percentile rankings reinforce the verdict. The M460 at the 38th percentile is a mid-tier mobile part, while the HD 8790M at the 33rd percentile sits just below. For a buyer choosing between two used or refurbished laptops, the M460 offers the better performance ceiling. For a user specifically targeting Vulkan-based games or applications, the HD 8790M’s Vulkan efficiency could make it a viable alternative, but the overall average benchmark score still favors the M460.

Where Each One Wins

The AMD Radeon R7 M460 wins in the only direct head-to-head benchmark recorded: Geekbench OpenCL. This suggests it is the stronger choice for OpenCL-accelerated tasks such as video transcoding, image processing, scientific computing, or any workload that leverages the OpenCL standard. Its 6612 score is also higher than the HD 8790M’s best result in any single test, making it the safer all-around pick.

The AMD Radeon HD 8790M wins in the Vulkan API category, where its 6365 score exceeds its own OpenCL result by 26.9%. While there is no direct Vulkan comparison between the two cards in the database, the HD 8790M’s Vulkan score is within 3.7% of the M460’s OpenCL score. This implies that in Vulkan-specific scenarios, the HD 8790M could perform at a level comparable to the M460’s OpenCL performance, potentially making it the better option for Vulkan-native titles.

The HD 8790M also holds an advantage in memory bandwidth. Its 128-bit bus width and 64.00 GB/s bandwidth double the M460’s 64-bit bus and 36.00 GB/s bandwidth. This could benefit memory-intensive workloads that are not purely compute-bound, even if the raw shader throughput is lower.

FAQ

Q: Which GPU is faster in OpenCL compute benchmarks?

A: The AMD Radeon R7 M460 scores 6612 in Geekbench OpenCL, which is 31.8% higher than the HD 8790M’s 5017 in the same test.

Q: Does the HD 8790M have any performance advantage at all?

A: Yes, its Geekbench Vulkan score of 6365 is much higher than its own OpenCL score and comes within 3.7% of the M460’s OpenCL result, suggesting it handles Vulkan workloads more efficiently.

Q: How do these cards compare to their closest rivals?

A: The M460 trades blows within a 1.5% range around the HD 7730M, UHD Graphics P750, GT 1010, and GTX 670M. The HD 8790M similarly stays within 1.6% of the Iris Pro P6300, GTX 670MX, GTX 550 Ti, and Quadro M500M.

Q: What is the memory configuration difference?

A: Both cards have 2 GB of GDDR5, but the HD 8790M uses a 128-bit bus with 64.00 GB/s bandwidth, while the M460 uses a 64-bit bus with 36.00 GB/s bandwidth.

Q: Which card has a higher pixel fill rate?

A: The M460 achieves 8.192 GPixel/s, which is 13.8% higher than the HD 8790M’s 7.200 GPixel/s.

Q: Are both cards end-of-life products?

A: Yes, both the R7 M460 and the HD 8790M are listed as end-of-life in the database, with release dates of May 2016 and March 2013 respectively.

Architecture Differences

The two GPUs share a common manufacturer and process node, but their internal designs diverge significantly. Both are built by TSMC on a 28 nm process, yet the transistor counts tell different stories. The R7 M460 packs 1,550 million transistors on a 125 mm² die, yielding a transistor density of 12.4 million per square millimeter. The HD 8790M is a smaller chip with 950 million transistors on a 77 mm² die, resulting in a nearly identical density of 12.3 million per square millimeter. The M460’s larger die and higher transistor count are the physical foundation for its performance lead.

Architecturally, the R7 M460 uses GCN 3.0 while the HD 8790M uses the older GCN 1.0. This generational leap is reflected in the API support: the M460 supports DirectX 12 (12_0), whereas the HD 8790M is limited to DirectX 12 (11_1). Both cards support OpenGL 4.6 and Vulkan 1.2.170, so the practical API difference is primarily in DirectX feature levels. The M460 belongs to the Gem System generation (R7 M400 series), while the HD 8790M is from the Solar System generation (HD 8700M series). The HD 8790M’s successor is listed as the Gem System, confirming that the M460 is the direct replacement.

Clock speeds also differ. The R7 M460 has a base clock of 730 MHz and a boost clock of 1024 MHz, a boost ratio of roughly 40%. The HD 8790M runs at 850 MHz base and 900 MHz boost, a much smaller boost window of about 6%. Despite the M460’s lower base clock, its higher boost clock and architectural improvements deliver the performance advantage. Memory clocks are similar: the M460 runs at 1125 MHz (4.5 Gbps effective), while the HD 8790M runs at 1000 MHz (4 Gbps effective). The HD 8790M compensates with its wider 128-bit memory bus, doubling the bandwidth to 64.00 GB/s versus the M460’s 36.00 GB/s.

Both cards have identical shading units (384), texture mapping units (24), and render output units (8). The raw compute rates, however, favor the M460: it delivers 786.4 GFLOPS FP32 versus the HD 8790M’s 691.2 GFLOPS, a 13.8% difference. The M460 also supports FP16 at a 1:1 ratio (786.4 GFLOPS), while the HD 8790M has no recorded FP16 capability.

The form factor and connectivity differ as well. The HD 8790M is an MXM Module with no power connectors and MXM-A (3.0) bus interface, designed for portable devices with vendor-dependent display outputs. The M460 uses PCIe 3.0 x8, a more standard mobile interface. The HD 8790M was released in March 2013, while the M460 arrived in May 2016, a gap of over three years that explains the architectural generational shift.