AMD Radeon HD 8790M vs AMD Radeon R7 240 Comparison
AMD Radeon HD 8790M
Radeon R7 240
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon HD 8790M vs AMD Radeon R7 240
FAQ
Q: How do the two GPUs compare in raw compute performance?
A: The AMD Radeon HD 8790M delivers 691.2 GFLOPS of FP32 throughput, while the AMD Radeon R7 240 delivers 499.2 GFLOPS. The HD 8790M holds a 38% advantage in theoretical compute.
Q: What memory configuration does each card use?
A: The HD 8790M uses 2 GB of GDDR5 on a 128-bit bus with 64.00 GB/s bandwidth. The R7 240 uses 2 GB of DDR3 on a 128-bit bus with 28.80 GB/s bandwidth. The HD 8790M offers more than double the memory bandwidth.
Q: Which GPU wins the recorded head-to-head benchmark?
A: The R7 240 wins the only shared benchmark test, Geekbench OpenCL, with a score of 5063 versus 5017 for the HD 8790M, a delta of -0.9% for the HD 8790M.
Q: What are the core configurations of each GPU?
A: The HD 8790M has 384 shading units, 24 texture mapping units, and 8 raster operation units. The R7 240 has 320 shading units, 20 texture mapping units, and 8 raster operation units.
Q: How do the clock speeds compare?
A: The HD 8790M runs at a base clock of 850 MHz and a boost clock of 900 MHz. The R7 240 runs at a base clock of 730 MHz and a boost clock of 780 MHz. The HD 8790M has higher clocks in both states.
Q: What is the percentile ranking for each GPU in the database?
A: The HD 8790M sits at the 33rd percentile of all GPUs, while the R7 240 sits at the 30th percentile. The HD 8790M also has a higher average benchmark score of 5691 versus 5063 for the R7 240.
Architecture Differences
Both GPUs are built on AMD's GCN 1.0 architecture and manufactured on the same 28 nm process at TSMC. Both chips contain 950 million transistors on a 77 mm² die, giving a transistor density of 12.3M per mm². The architectural lineage differs: the HD 8790M belongs to the Solar System generation (HD 8700M series) with the chip codename Mars, while the R7 240 belongs to the Volcanic Islands generation (R7 200 series) with the chip codename Oland.
The HD 8790M uses a more compute-heavy configuration. It packs 384 shading units, 24 TMUs, and 8 ROPs. The R7 240 scales down to 320 shading units and 20 TMUs, while keeping 8 ROPs. This translates into a higher texture rate for the HD 8790M: 21.60 GTexel/s versus 15.60 GTexel/s for the R7 240. Pixel rates also diverge, with the HD 8790M at 7.200 GPixel/s and the R7 240 at 6.240 GPixel/s.
Memory architecture separates the two more sharply. The HD 8790M uses GDDR5 memory clocked at 1000 MHz with 4 Gbps effective transfer, resulting in 64.00 GB/s of bandwidth. The R7 240 uses DDR3 memory at 900 MHz with 1800 Mbps effective transfer, yielding only 28.80 GB/s. Both share a 128-bit memory bus and 2 GB capacity, but the memory type difference creates a large bandwidth gap.
The HD 8790M is designed as an MXM module with an MXM-A (3.0) bus interface, while the R7 240 is a single-slot desktop card with a PCIe 3.0 x8 interface. The HD 8790M's display outputs are portable device dependent, whereas the R7 240 provides 1x DVI, 1x HDMI 1.4a, and 1x VGA. The R7 240 has a rated TDP of 30 W and a suggested PSU of 200 W; the HD 8790M has no recorded TDP in the database. Neither card requires additional power connectors.
Head-to-Head Benchmarks
The database contains one shared benchmark between these two GPUs: Geekbench OpenCL. The R7 240 scores 5063, edging out the HD 8790M's 5017 by a margin of 0.9%. This is a narrow victory, well within typical run-to-run variance for synthetic workloads. The data shows that despite the HD 8790M's substantially higher theoretical compute (691.2 GFLOPS versus 499.2 GFLOPS), the R7 240 manages a slightly better OpenCL result.
Looking at the broader benchmark picture, the HD 8790M also has a Geekbench Vulkan score of 6365, a test that the R7 240 does not appear in. The HD 8790M's average benchmark score across all recorded tests is 5691, while the R7 240's average is 5063. This puts the HD 8790M roughly 12% ahead in aggregate performance, even though the single OpenCL comparison favors the R7 240.
The nearest rivals for each GPU help contextualize these scores. The HD 8790M sits near the Intel Iris Pro Graphics P6300 (5712, delta -0.4%), the NVIDIA GeForce GTX 670MX (5721, delta -0.5%), and the NVIDIA GeForce GTX 550 Ti (5731, delta -0.7%). The R7 240 is essentially tied with the AMD Radeon R7 M340 (5063, delta 0%), and slightly ahead of the AMD FirePro W4170M (5034, delta 0.6%) and AMD Radeon R5 M430 (5018, delta 0.9%). These proximity figures suggest both GPUs occupy a similar performance class, despite the HD 8790M's higher theoretical specs.
Specification Differences
| Specification | AMD Radeon HD 8790M | AMD Radeon R7 240 |
|---|---|---|
| Chip | Mars | Oland |
| Generation | Solar System (HD 8700M) | Volcanic Islands (R7 200) |
| Base Clock | 850 MHz | 730 MHz |
| Boost Clock | 900 MHz | 780 MHz |
| Memory Clock | 1000 MHz, 4 Gbps effective | 900 MHz, 1800 Mbps effective |
| Memory Type | GDDR5 | DDR3 |
| Bandwidth | 64.00 GB/s | 28.80 GB/s |
| Shading Units | 384 | 320 |
| TMUs | 24 | 20 |
| Pixel Rate | 7.200 GPixel/s | 6.240 GPixel/s |
| Texture Rate | 21.60 GTexel/s | 15.60 GTexel/s |
| FP32 | 691.2 GFLOPS | 499.2 GFLOPS |
| TDP | Not recorded | 30 W |
| Slot Width | MXM Module | Single-slot |
| Bus Interface | MXM-A (3.0) | PCIe 3.0 x8 |
| Display Outputs | Portable Device Dependent | 1x DVI, 1x HDMI 1.4a, 1x VGA |
| Suggested PSU | Not recorded | 200 W |
| Dimensions | Not recorded | 168 mm (6.6 inches) length, 69 mm (2.7 inches) height |
| Release Date | 2013-03-31 | 2013-10-07 |
| Predecessor | London | Sea Islands |
| Successor | Gem System | Pirate Islands |
| Launch MSRP | Not recorded | 69 USD |
| Geekbench OpenCL | 5017 | 5063 |
| Geekbench Vulkan | 6365 | Not recorded |
| Avg Benchmark Score | 5691 | 5063 |
| Percentile | 33 | 30 |
The Verdict
The data presents a split picture. In raw hardware specifications, the HD 8790M is clearly the stronger GPU: higher clocks, more shading units, more TMUs, GDDR5 memory, more than double the bandwidth, and 38% more FP32 compute. Its average benchmark score of 5691 versus 5063 for the R7 240 confirms this hardware advantage in aggregate.
However, the only direct head-to-head comparison, Geekbench OpenCL, goes to the R7 240 with a score of 5063 versus 5017. This suggests that in certain compute workloads, the R7 240's architecture or driver path can compensate for its lower theoretical specs. The HD 8790M also has a Vulkan score of 6365, indicating stronger performance in that API, though no direct R7 240 comparison exists for Vulkan.
The percentile rankings place the HD 8790M at the 33rd percentile and the R7 240 at the 30th percentile of all GPUs. The HD 8790M's nearest rivals (Intel Iris Pro P6300, GTX 670MX, GTX 550 Ti) all score in the 5712-5731 range, while the R7 240's nearest rivals (R7 M340, FirePro W4170M, R5 M430) score in the 5018-5063 range. This confirms that the HD 8790M operates in a slightly higher performance tier overall.
Where Each One Wins
The HD 8790M wins on every theoretical compute metric: pixel rate (7.200 versus 6.240 GPixel/s), texture rate (21.60 versus 15.60 GTexel/s), and FP32 throughput (691.2 versus 499.2 GFLOPS). Its GDDR5 memory with 64.00 GB/s bandwidth gives it a massive advantage in bandwidth-sensitive workloads, which typically include higher-resolution textures, anti-aliasing, and compute tasks that stream large data sets. The Vulkan score of 6365 suggests it handles modern API workloads well.
The R7 240 wins the single recorded OpenCL benchmark by 0.9%, indicating that its lower clocked DDR3 configuration can still match or slightly exceed the HD 8790M in certain compute patterns. It also carries a rated TDP of 30 W and a suggested PSU of 200 W, which the HD 8790M lacks in recorded data. The R7 240's desktop form factor with PCIe 3.0 x8 and three display outputs (DVI, HDMI 1.4a, VGA) makes it a more flexible option for conventional desktop setups, whereas the HD 8790M's MXM module targets portable devices.
The release dates show the R7 240 launched later (2013-10-07 versus 2013-03-31), and its generation lineage (Volcanic Islands) is newer than the HD 8790M's Solar System generation. The R7 240's launch MSRP is recorded as 69 USD. The HD 8790M has no recorded launch MSRP. For users prioritizing raw compute and memory bandwidth, the HD 8790M's data is stronger. For users who need a low-TDP, single-slot desktop card with multiple display outputs and a slight edge in the one shared OpenCL test, the R7 240's data supports that choice.