AMD Radeon HD 7790 vs NVIDIA T400 Comparison

The AMD Radeon HD 7790 and the NVIDIA T400 are two end-of-life graphics cards separated by nearly a decade of architecture evolution, yet their benchmark scores place them in a surprisingly close performance class. The HD 7790 achieves a Geekbench Metal score of 17,666, which is 7.0% higher than the T400’s average benchmark score of 16,508 across its OpenCL and Vulkan tests. However, the data reveals that the T400 is the more versatile and efficient option, with a 60th percentile ranking versus the HD 7790’s 61st, indicating that while their overall performance is comparable, their strengths lie in completely different areas of the workload spectrum.

Where Each One Wins

The performance split between these two cards is defined by their respective benchmark submissions. The AMD Radeon HD 7790’s sole benchmark result is a Geekbench Metal score of 17,666, which places it 0.2% ahead of the NVIDIA GeForce RTX 4060 and 0.4% ahead of the AMD Radeon 780M. This indicates that in Metal-based compute tasks, the HD 7790 holds a measurable, albeit narrow, edge over modern integrated graphics and even some contemporary discrete GPUs. The data suggests that the HD 7790 is the superior choice for applications that leverage Apple’s Metal API, where its GCN architecture still delivers competitive compute throughput.

The NVIDIA T400, conversely, has results in two separate APIs: Geekbench OpenCL at 17,039 and Geekbench Vulkan at 15,976. Its OpenCL score is particularly strong, outperforming its own Vulkan result by 6.7% and coming within 3.6% of the HD 7790’s Metal score. The T400’s Vulkan score of 15,976, while lower, is still a significant result that places it 3.2% behind its own OpenCL performance. This indicates that the T400 is the more flexible card for cross-platform compute workloads, offering solid performance in both OpenCL and Vulkan environments, whereas the HD 7790’s single Metal result leaves its OpenCL and Vulkan capabilities undocumented in this data set.

Architecture Differences

The architectural divide between these two GPUs is substantial. The AMD Radeon HD 7790 is built on the Bonaire chip using GCN 2.0 architecture, manufactured on a 28 nm process at TSMC. It contains 2,080 million transistors on a 160 mm² die, resulting in a transistor density of 13.0M per mm². The NVIDIA T400, in contrast, uses the TU117 chip with Turing architecture, fabricated on a 12 nm process, also at TSMC. The T400 packs 4,700 million transistors onto a 200 mm² die, achieving a significantly higher transistor density of 23.5M per mm².

The memory subsystems diverge sharply. The HD 7790 features 1024 MB of GDDR5 memory on a 128-bit bus, delivering a bandwidth of 96.00 GB/s. The T400 offers 2 GB of GDDR6 memory on a narrower 64-bit bus, producing 80.00 GB/s of bandwidth. Despite having 16.7% less raw bandwidth, the T400 doubles the memory capacity, which is critical for larger datasets. The compute configurations also differ: the HD 7790 has 896 shading units, 56 texture mapping units, and 16 ROPs, while the T400 has 384 shading units, 24 TMUs, and 16 ROPs. The HD 7790 leads in raw shading and texture throughput, but the T400 counters with higher clock speeds, boosting from a 420 MHz base to 1425 MHz, whereas the HD 7790’s clocks are not listed.

The Verdict

For users prioritizing Metal-based compute performance, the AMD Radeon HD 7790 is the data-backed choice. Its 17,666 Metal score is the highest single benchmark result between the two cards, and it edges out the T400’s best OpenCL score by 3.7%. The HD 7790 also offers superior texture fill rate at 56.00 GTexel/s versus the T400’s 34.20 GTexel/s, and a higher FP32 throughput of 1.792 TFLOPS against the T400’s 1,094.4 GFLOPS. If the workload is strictly compute-heavy on Metal, the HD 7790 wins.

The NVIDIA T400 is the better all-rounder for modern multi-API environments. It delivers strong OpenCL performance at 17,039, which is only 3.6% behind the HD 7790’s Metal score, and adds Vulkan support at 15,976, which the HD 7790 lacks in this data. The T400’s 30 W TDP is 64.7% lower than the HD 7790’s 85 W, and it requires no power connectors versus the HD 7790’s 1x 6-pin. The T400 also has double the memory capacity at 2 GB, supports DirectX 12_1 versus the HD 7790’s 12_0, and offers Vulkan 1.4 support against the HD 7790’s 1.2.170. For efficiency, modern API coverage, and memory capacity, the T400 is the superior choice.

FAQ

Q: Which card has a higher average benchmark score?

A: The AMD Radeon HD 7790 has a higher average benchmark score of 17,666, while the NVIDIA T400 averages 16,508 across its two benchmark results.

Q: How do their memory capacities and bandwidth compare?

A: The T400 has 2 GB of GDDR6 memory, double the HD 7790’s 1024 MB of GDDR5. The HD 7790 has higher bandwidth at 96.00 GB/s, while the T400 provides 80.00 GB/s.

Q: What are the power requirement differences?

A: The T400 has a 30 W TDP and requires no power connectors, while the HD 7790 has an 85 W TDP and requires a single 6-pin power connector. The T400 also has a lower suggested PSU of 200 W versus 250 W for the HD 7790.

Q: Which card supports more modern graphics APIs?

A: The NVIDIA T400 supports DirectX 12 (12_1) and Vulkan 1.4, while the AMD Radeon HD 7790 supports DirectX 12 (12_0) and Vulkan 1.2.170. Both support OpenGL 4.6.

Q: How does the T400’s Vulkan performance compare to its OpenCL performance?

A: The T400 scores 15,976 in Geekbench Vulkan, which is 6.2% lower than its Geekbench OpenCL score of 17,039.

Q: What is the transistor density difference between the two chips?

A: The NVIDIA T400 has a much higher transistor density of 23.5M per mm², while the AMD Radeon HD 7790 has a density of 13.0M per mm².

Head-to-Head Benchmarks

The most significant performance comparison comes from the HD 7790’s Geekbench Metal score of 17,666 against the T400’s Geekbench OpenCL score of 17,039. This 3.7% difference in favor of the HD 7790 is the largest single-benchmark gap between the two cards. The HD 7790’s Metal result also places it 0.2% ahead of the GeForce RTX 4060, a modern GPU, and 0.7% ahead of the AMD Radeon Pro 560. This suggests that in Metal compute, the HD 7790’s older GCN architecture still performs competitively against much newer hardware.

The T400’s OpenCL score of 17,039 is its strongest showing, and it is only 0.4% behind the HD 7790’s Metal result. The T400’s closest rival in this score range is the AMD Radeon 780M at 17,588, which the T400 trails by 3.2%. The T400’s Vulkan score of 15,976 is its weakest result, placing it 0.9% ahead of the AMD Radeon RX 5700 XT, but 6.7% behind its own OpenCL performance. In the broader context of the T400’s nearest rivals, its average score of 16,508 is essentially tied with the GeForce RTX 5090 D V2, which scores 16,504 with a 0% delta, and 0.6% ahead of the Radeon PRO W7500 and RTX PRO 6000 Blackwell.

Specification Differences

The two cards differ fundamentally in their physical and electrical specifications. The AMD Radeon HD 7790 measures 183 mm in length (7.2 inches) and occupies a dual-slot form factor, while the NVIDIA T400 is a single-slot card with no listed dimensions. The HD 7790 requires a 1x 6-pin power connector and has a 250 W suggested PSU, whereas the T400 needs no power connectors and has a 200 W suggested PSU. The TDP difference is stark: 85 W for the HD 7790 versus 30 W for the T400.

In terms of display outputs, the HD 7790 offers 1x DVI, 1x HDMI 1.4a, and 2x mini-DisplayPort 1.2, while the T400 provides 3x mini-DisplayPort 1.4a. The HD 7790’s memory operates at 1500 MHz (6 Gbps effective) with a 128-bit bus, while the T400’s memory runs at 1250 MHz (10 Gbps effective) on a 64-bit bus. The HD 7790 has a pixel rate of 16.00 GPixel/s and a texture rate of 56.00 GTexel/s, compared to the T400’s 22.80 GPixel/s and 34.20 GTexel/s. The release dates differ by over eight years: the HD 7790 launched on 2013-03-21, while the T400 launched on 2021-05-05. The HD 7790 had a launch MSRP of 149 USD, while the T400 has no listed launch MSRP.