AMD Radeon HD 8790M vs AMD Radeon R7 M260X Comparison

Head-to-Head Benchmarks

The recorded data shows a split decision between these two mobile graphics processors. Each wins one of the two tracked benchmarks, and the margins are substantial in both directions.

In Geekbench OpenCL, the AMD Radeon R7 M260X posts a score of 5690, which is 11.8% ahead of the AMD Radeon HD 8790M's 5017. This is a clear victory for the newer part in compute-oriented workloads that leverage OpenCL acceleration. The R7 M260X's advantage here is not marginal; it is a double-digit percentage gap that places it in a distinctly higher performance tier for this specific API.

However, the story reverses sharply in Geekbench Vulkan. The AMD Radeon HD 8790M scores 6365, while the AMD Radeon R7 M260X manages only 4631. That translates to a 37.4% lead for the HD 8790M, a massive swing in the opposite direction. The HD 8790M's Vulkan result is not just a narrow win; it is a dominant performance advantage that dwarfs the R7 M260X's OpenCL lead.

Looking at the average benchmark score, which combines both tests, the HD 8790M comes out ahead with 5691 versus 5161 for the R7 M260X. The HD 8790M's average is also higher than three of its four nearest rivals in the database. It sits within 0.4% of the Intel Iris Pro Graphics P6300, within 0.5% of the NVIDIA GeForce GTX 670MX, and within 0.7% of the NVIDIA GeForce GTX 550 Ti. The R7 M260X, by contrast, sits within 0.1% of the NVIDIA Quadro K3100M, within 1% of the NVIDIA Quadro 4000M, and within 1.4% of the NVIDIA GeForce GTX 760M.

The delta percentages against nearest rivals reveal how each chip positions itself. The HD 8790M is 1.6% ahead of the NVIDIA Quadro M500M, while the R7 M260X is 1.9% ahead of the AMD Radeon R7 240. Neither chip dominates its closest competitors, but the HD 8790M's nearest rivals are all scoring in the 5600 to 5730 range, whereas the R7 M260X's nearest rivals cluster in the 5060 to 5240 range. That is a meaningful difference in overall competitive positioning.

The Verdict

Based strictly on benchmark data, the AMD Radeon HD 8790M is the stronger overall performer. Its average benchmark score of 5691 exceeds the R7 M260X's 5161 by roughly 10%. The HD 8790M also holds a higher percentile rank among all GPUs, sitting at the 33rd percentile compared to the R7 M260X's 30th percentile.

Users who prioritize Vulkan-based workloads or gaming titles that use the Vulkan API should choose the HD 8790M without hesitation. Its 37.4% advantage in that benchmark is decisive and unlikely to be offset by other factors. The HD 8790M's Vulkan score of 6365 is also higher than its own OpenCL score, indicating strong driver support and architectural efficiency for modern low-level APIs.

Users who prioritize OpenCL compute tasks, such as certain rendering, video encoding, or scientific workloads, should favor the R7 M260X. Its 11.8% lead in OpenCL makes it the better option for those specific applications. The R7 M260X also benefits from a later release date in the database, which may imply longer driver support in some ecosystems, though the recorded data does not quantify that.

The overall verdict is that the HD 8790M is the better all-around mobile GPU for mixed workloads, while the R7 M260X is a specialized choice for OpenCL-heavy usage. Neither card is a clear winner across the board, and the choice ultimately depends on which API the user's software relies on most heavily.

Architecture Differences

Both GPUs are built by AMD and share the same GCN 1.0 architecture. They are also fabricated on the same 28 nm process at TSMC, with an identical transistor count of 950 million and an identical die size of 77 mm². The transistor density is likewise the same at 12.3 million transistors per square millimeter.

The underlying compute resources are identical in count. Both chips feature 384 shading units, 24 texture mapping units, and 8 raster operations pipelines. There are no ray tracing cores or tensor cores on either chip, consistent with their GCN 1.0 design era.

The key architectural difference lies in the chip designations and clock speeds. The HD 8790M uses the Mars chip, while the R7 M260X uses the Opal chip. Despite the different names, the core configuration is the same, but the clock behavior diverges significantly. The HD 8790M has a base clock of 850 MHz and a boost clock of 900 MHz. The R7 M260X operates at a lower base clock of 620 MHz and a boost clock of 715 MHz.

These clock differences directly impact pixel and texture throughput. The HD 8790M achieves a pixel rate of 7.200 GPixel/s and a texture rate of 21.60 GTexel/s. The R7 M260X, with its lower clocks, delivers only 5.720 GPixel/s and 17.16 GTexel/s. Floating point performance follows the same pattern: the HD 8790M produces 691.2 GFLOPS of FP32 compute, while the R7 M260X produces 549.1 GFLOPS.

Memory configurations are similar in type and bus width, both using GDDR5 on a 128-bit bus with a bandwidth of 64.00 GB/s. The effective memory clock is also identical at 4 Gbps. The difference is capacity: the HD 8790M carries 2 GB, while the R7 M260X carries 1024 MB (1 GB).

The bus interface differs as well. The HD 8790M uses an MXM-A (3.0) connector, while the R7 M260X uses PCIe 3.0 x8. Both are designed for portable devices with display outputs listed as "Portable Device Dependent." Neither requires external power connectors.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon HD 8790M has an average benchmark score of 5691, compared to 5161 for the AMD Radeon R7 M260X.

Q: How large is the Vulkan performance gap between the two?

A: The HD 8790M scores 6365 in Geekbench Vulkan, which is 37.4% higher than the R7 M260X's score of 4631.

Q: Does the R7 M260X win any benchmark?

A: Yes, in Geekbench OpenCL the R7 M260X scores 5690, which is 11.8% ahead of the HD 8790M's 5017.

Q: Are the core counts the same on both chips?

A: Yes, both the Mars chip in the HD 8790M and the Opal chip in the R7 M260X feature 384 shading units, 24 TMUs, and 8 ROPs.

Q: What is the memory capacity difference?

A: The HD 8790M has 2 GB of GDDR5 memory, while the R7 M260X has 1024 MB (1 GB) of GDDR5 memory. Both use a 128-bit bus with 64.00 GB/s bandwidth.

Q: Which GPU has a higher base clock?

A: The HD 8790M has a base clock of 850 MHz and a boost clock of 900 MHz, while the R7 M260X has a base clock of 620 MHz and a boost clock of 715 MHz.

Where Each One Wins

The AMD Radeon HD 8790M wins in Vulkan-based workloads, as demonstrated by its 37.4% lead in Geekbench Vulkan. This makes it the superior choice for modern games and applications that use Vulkan for rendering or compute. Its higher clocks also give it advantages in pixel rate (7.200 GPixel/s versus 5.720 GPixel/s) and texture rate (21.60 GTexel/s versus 17.16 GTexel/s), which can benefit any workload that is fill-rate limited, regardless of API. The HD 8790M also has double the memory capacity at 2 GB, which may help in scenarios where texture data exceeds 1 GB.

The AMD Radeon R7 M260X wins in OpenCL compute workloads, with an 11.8% advantage in Geekbench OpenCL. This makes it the better option for users running OpenCL-accelerated tasks such as video encoding, image processing, or general-purpose GPU compute. The R7 M260X also holds a slight edge in its nearest-rival comparison, sitting 1.9% ahead of the AMD Radeon R7 240, whereas the HD 8790M is 0.4% behind its closest rival, the Intel Iris Pro Graphics P6300. The R7 M260X also has a later release date in the database, which may correlate with more recent driver optimizations for OpenCL paths.

For overall average performance, the HD 8790M wins by a comfortable margin, so users who cannot predict their workload mix should default to the HD 8790M. For users with known OpenCL-heavy workloads, the R7 M260X's 5690 score in that specific test makes it the targeted choice.

Specification Differences

The two GPUs differ in several specification fields, while sharing many others. The chip designations are different: the HD 8790M uses the Mars chip, and the R7 M260X uses the Opal chip. The generation names also differ, with the HD 8790M belonging to the Solar System (HD 8700M) generation and the R7 M260X belonging to the Gem System (R7 M200) generation.

Clock speeds differ substantially. The HD 8790M has a base clock of 850 MHz and a boost clock of 900 MHz. The R7 M260X has a base clock of 620 MHz and a boost clock of 715 MHz.

Memory capacity differs: the HD 8790M has 2 GB, while the R7 M260X has 1024 MB. Both use GDDR5 on a 128-bit bus with identical 64.00 GB/s bandwidth and 4 Gbps effective memory clock.

Pixel rate and texture rate differ due to clocks. The HD 8790M achieves 7.200 GPixel/s and 21.60 GTexel/s. The R7 M260X achieves 5.720 GPixel/s and 17.16 GTexel/s. FP32 performance also differs, with the HD 8790M at 691.2 GFLOPS and the R7 M260X at 549.1 GFLOPS.

The bus interface differs: the HD 8790M uses MXM-A (3.0), while the R7 M260X uses PCIe 3.0 x8. The release dates differ as well, with the HD 8790M released on 2013-03-31 and the R7 M260X released on 2015-12-05. The predecessor and successor fields also differ, with the HD 8790M listing London as predecessor and Gem System as successor, while the R7 M260X lists Solar System as predecessor and Polaris Mobile as successor.

The two share the same process node (28 nm), foundry (TSMC), transistor count (950 million), die size (77 mm²), transistor density (12.3M / mm²), shading units (384), TMUs (24), ROPs (8), memory type (GDDR5), memory bus width (128 bit), memory bandwidth (64.00 GB/s), power connector requirement (None), display output type (Portable Device Dependent), DirectX support (12 (11_1)), OpenGL support (4.6), Vulkan support (1.2.170), and production status (End-of-life).