AMD Radeon HD 8790M vs NVIDIA GeForce GTX 460 SE Comparison

The Verdict

The recorded data presents a clear split between these two end-of-life mobile and desktop GPUs. The NVIDIA GeForce GTX 460 SE holds a decisive advantage in the single available OpenCL benchmark, scoring 6389 against the AMD Radeon HD 8790M's 5017, a 27.3% lead. For any workload that relies on OpenCL compute performance, the GTX 460 SE is the stronger choice based strictly on these measurements.

The AMD Radeon HD 8790M, however, is not without its own merits. It supports the Vulkan API at version 1.2.170, a capability the GTX 460 SE entirely lacks, and it offers double the memory at 2 GB versus 1024 MB. The GTX 460 SE also lacks any Vulkan support in the database, so for modern Vulkan-based applications, the AMD part is the only functional option between the two.

The GTX 460 SE sits at the 37th percentile of all GPUs, while the HD 8790M sits at the 33rd percentile. The desktop card also has a higher average benchmark score of 6389 compared to 5691 for the mobile part. Users needing peak compute throughput in OpenCL should choose the GTX 460 SE. Users needing Vulkan compatibility, more memory capacity, or a mobile form factor should choose the HD 8790M.

Architecture Differences

The two GPUs come from different architectural generations and process nodes. The NVIDIA GeForce GTX 460 SE is built on the Fermi architecture using the GF104 chip, manufactured on a 40 nm process at TSMC. The AMD Radeon HD 8790M uses the GCN 1.0 architecture with the Mars chip, built on a more advanced 28 nm process, also at TSMC.

The transistor counts differ substantially. The GTX 460 SE packs 1,950 million transistors on a 332 mm² die, resulting in a transistor density of 5.9 million transistors per square millimeter. The HD 8790M contains 950 million transistors on a much smaller 77 mm² die, achieving a higher density of 12.3 million per square millimeter. This reflects the newer process node and a more compact design for the AMD part, which is intended for portable devices.

Memory configurations also diverge. The GTX 460 SE has 1024 MB of GDDR5 memory on a 256-bit bus, delivering 108.8 GB/s of bandwidth. The HD 8790M has 2 GB of GDDR5 memory on a 128-bit bus, yielding 64.00 GB/s of bandwidth. The NVIDIA card has a wider memory interface and substantially higher bandwidth, while the AMD card offers double the capacity. Memory clocks are recorded at 850 MHz (3.4 Gbps effective) for the GTX 460 SE and 1000 MHz (4 Gbps effective) for the HD 8790M.

The compute resources are organized differently. The GTX 460 SE has 288 shading units, 48 texture mapping units, and 32 ROPs. The HD 8790M has 384 shading units but only 24 TMUs and 8 ROPs. Pixel rates are close, with the GTX 460 SE at 7.800 GPixel/s and the HD 8790M at 7.200 GPixel/s. Texture rate favors the NVIDIA card at 31.20 GTexel/s versus 21.60 GTexel/s. FP32 performance is 748.8 GFLOPS for the GTX 460 SE and 691.2 GFLOPS for the HD 8790M.

Power and physical characteristics differ as well. The GTX 460 SE is a dual-slot desktop card with a 150 W TDP, two 6-pin power connectors, a suggested 450 W power supply, and a 210 mm (8.3 inches) length. It uses a PCIe 2.0 x16 interface and outputs 2x DVI and 1x mini-HDMI 1.3a. The HD 8790M is an MXM Module with no power connectors listed, an MXM-A (3.0) interface, and display outputs dependent on the portable device. It has no recorded TDP or suggested PSU.

API support shows a key differentiator. Both support DirectX 12, but the GTX 460 SE is listed at 12 (11_0) while the HD 8790M is at 12 (11_1). Both support OpenGL 4.6. The HD 8790M supports Vulkan 1.2.170, while the GTX 460 SE has no Vulkan support recorded. The GTX 460 SE was released in November 2010 with a launch MSRP of 160 USD, while the HD 8790M was released in March 2013.

Where Each One Wins

The GTX 460 SE wins in raw compute throughput. Its OpenCL score of 6389 is 27.3% higher than the HD 8790M's 5017. This advantage is consistent with its higher FP32 output, higher texture rate, and wider memory bus. Applications that stress pixel fill and texture filtering will also favor the NVIDIA card, given its 7.800 GPixel/s versus 7.200 GPixel/s and 31.20 GTexel/s versus 21.60 GTexel/s.

The HD 8790M wins in API coverage and memory capacity. It is the only one of the two with Vulkan support, and its 2 GB frame buffer is double that of the GTX 460 SE. For workloads that exceed 1 GB of memory usage, the AMD card has a clear capacity advantage, even though its bandwidth is lower at 64.00 GB/s versus 108.8 GB/s. The HD 8790M also has a higher shading unit count at 384 versus 288, though this does not translate into a higher benchmark score in the recorded data.

The HD 8790M also shows Vulkan performance in the database with a score of 6365, which is close to the GTX 460 SE's OpenCL score of 6389. This suggests that in Vulkan workloads, the AMD part can approach the performance level the NVIDIA card achieves in OpenCL. The GTX 460 SE has no Vulkan score recorded, so no direct comparison is possible.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 460 SE scores 6389 in Geekbench OpenCL, while the AMD Radeon HD 8790M scores 5017. The GTX 460 SE is 27.3% ahead.

Q: Does the NVIDIA GeForce GTX 460 SE support Vulkan?

A: No. The database records no Vulkan support for the GTX 460 SE. The AMD Radeon HD 8790M supports Vulkan version 1.2.170.

Q: Which GPU has more memory?

A: The AMD Radeon HD 8790M has 2 GB of GDDR5 memory. The NVIDIA GeForce GTX 460 SE has 1024 MB of GDDR5 memory. The AMD card offers double the capacity.

Q: How do their memory bandwidth figures compare?

A: The NVIDIA GeForce GTX 460 SE has a 256-bit bus and delivers 108.8 GB/s. The AMD Radeon HD 8790M has a 128-bit bus and delivers 64.00 GB/s. The GTX 460 SE has higher bandwidth despite the AMD card's faster memory clock.

Q: What are the process nodes for these GPUs?

A: The NVIDIA GeForce GTX 460 SE is manufactured on a 40 nm process. The AMD Radeon HD 8790M is manufactured on a 28 nm process. Both use TSMC as the foundry.

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 460 SE has an average benchmark score of 6389. The AMD Radeon HD 8790M has an average of 5691. The GTX 460 SE also sits at a higher percentile, 37th versus 33rd.

Head-to-Head Benchmarks

The only directly comparable benchmark in the database is Geekbench OpenCL. The NVIDIA GeForce GTX 460 SE scores 6389, and the AMD Radeon HD 8790M scores 5017. The delta is 27.3% in favor of the NVIDIA card. This is the sole head-to-head test recorded, and it results in one win for the GTX 460 SE and zero wins for the HD 8790M.

This OpenCL result aligns with the underlying hardware specifications. The GTX 460 SE has a higher FP32 throughput at 748.8 GFLOPS versus 691.2 GFLOPS for the HD 8790M. The NVIDIA card also has a higher texture rate at 31.20 GTexel/s versus 21.60 GTexel/s, and a higher pixel rate at 7.800 GPixel/s versus 7.200 GPixel/s. The memory bandwidth gap is significant, with 108.8 GB/s versus 64.00 GB/s, which can heavily impact compute workloads that are memory-bound.

The AMD card shows a separate Vulkan benchmark score of 6365, but no Vulkan score exists for the GTX 460 SE. That means the HD 8790M can be compared to the GTX 460 SE's OpenCL performance only indirectly. The HD 8790M's Vulkan score of 6365 is nearly identical to the GTX 460 SE's OpenCL score of 6389, a difference of only 0.4%. However, these are different APIs, so they are not directly comparable in a head-to-head sense.

The nearest rivals for each GPU provide additional context. The GTX 460 SE is matched exactly by the NVIDIA GeForce GTX 580M, which also scores 6389, a delta of 0%. It trails the NVIDIA RTX PRO 5000 72 GB Blackwell by 0.3% (6407) and leads the AMD Radeon Pro WX 4100 by 0.9% (6330) and the AMD Radeon R7 M350 by 1% (6327). The HD 8790M's average score of 5691 is 0.4% behind the Intel Iris Pro Graphics P6300 (5712), 0.5% behind the NVIDIA GeForce GTX 670MX (5721), 0.7% behind the NVIDIA GeForce GTX 550 Ti (5731), and 1.6% ahead of the NVIDIA Quadro M500M (5604).

The data indicates that the GTX 460 SE competes at a performance tier roughly equivalent to a high-end mobile GPU like the GTX 580M, despite being a desktop part. The HD 8790M competes in a lower tier, near the GTX 550 Ti and GTX 670MX. The 27.3% OpenCL gap between the two reviewed GPUs is consistent with their relative positions in the overall database rankings.

In practical terms, the GTX 460 SE should be selected for OpenCL compute tasks where its 27.3% advantage directly translates to faster execution. The HD 8790M should be selected when the workload requires Vulkan API support, which the GTX 460 SE cannot provide, or when the 2 GB memory capacity is necessary for larger datasets. The GTX 460 SE's higher bandwidth also makes it more suitable for memory-intensive operations, while the HD 8790M's smaller die and mobile form factor suit portable systems.