AMD FirePro W600 vs AMD Radeon HD 8790M Comparison

Head-to-Head Benchmarks

The head-to-head comparison in the database is one-sided, with the AMD FirePro W600 winning the only shared benchmark test. In the Geekbench OpenCL test, the FirePro W600 scores 6223 against the Radeon HD 8790M’s 5017. That is a 24% advantage for the FirePro W600, a substantial margin that clearly separates the two desktop-oriented versus mobile-oriented designs.

Looking at the nearest rival data, the FirePro W600’s score of 6223 places it in close company with the AMD Radeon HD 6950, which averages 6210, a delta of just 0.2% in favor of the FirePro. It also sits within 0.7% of both the NVIDIA GeForce RTX 4070 Ti SUPER AD102 and the NVIDIA GeForce RTX 5070 Ti SUPER, which each score 6270. The NVIDIA Quadro K620 is 0.9% ahead at 6282. These deltas are small, but they confirm that the FirePro W600’s OpenCL performance is competitive with a range of much newer and more expensive GPUs, despite its age and end-of-life status.

The Radeon HD 8790M, by contrast, scores 5017 in OpenCL, but it also has a separate Vulkan result of 6365 in the database. That Vulkan score is notably higher than its OpenCL score, and it actually exceeds the FirePro W600’s OpenCL total. However, since the FirePro W600 has no recorded Vulkan benchmark, a direct head-to-head in that API cannot be established. What the data does show is that the 8790M’s average benchmark score across both tests is 5691, which is lower than the FirePro W600’s single-score average of 6223.

The 8790M’s nearest rivals further contextualize its standing. Its average score of 5691 is 0.4% below the Intel Iris Pro Graphics P6300 (5712), 0.5% below the NVIDIA GeForce GTX 670MX (5721), and 0.7% below the NVIDIA GeForce GTX 550 Ti (5731). The only rival it beats in this list is the NVIDIA Quadro M500M, which averages 5604, giving the 8790M a 1.6% edge. This places the mobile GPU in a lower performance tier than the FirePro W600, which is expected given the architectural differences in shader count, texture units, and ROPs.

The delta of 24% in OpenCL is the single largest gap between any two scores in this comparison. It is not a marginal difference; it is a decisive one. The FirePro W600’s higher pixel rate, texture rate, and FP32 throughput all contribute to this outcome, and the data reflects those specifications directly.

The Verdict

The data is unambiguous: the AMD FirePro W600 is the stronger GPU in OpenCL workloads, and it wins the only direct benchmark comparison. Its score of 6223 is 24% higher than the Radeon HD 8790M’s 5017 in the same test, and its average benchmark score of 6223 exceeds the 8790M’s average of 5691 by roughly 9.3%. If the choice is between these two for compute-heavy tasks that rely on OpenCL, the FirePro W600 is the clear pick.

However, the Radeon HD 8790M is not without a counterargument. Its Vulkan score of 6365 is higher than the FirePro W600’s OpenCL score, and since the FirePro has no recorded Vulkan result, the 8790M can claim superiority in that specific API. For users who prioritize Vulkan performance, the mobile GPU holds an edge that the database cannot refute. Additionally, the 8790M’s nearest rival comparisons show it clustering around older desktop cards like the GTX 550 Ti, which means it is not a weak performer for its class, but it is clearly below the FirePro W600.

The FirePro W600 also carries a 36th percentile ranking among all GPUs, while the 8790M sits at the 33rd percentile. That is a narrow difference in overall standing, but the direct benchmark gap is far larger. The percentile data suggests both are mid-to-low tier by modern standards, but within this pairing, the FirePro W600 is the better choice for raw compute.

For a workstation scenario, the FirePro W600’s single-slot design, six mini-DisplayPort outputs, and 75 W TDP make it a practical add-in card for multi-display setups. The 8790M, as an MXM module with portable-device-dependent outputs, is not designed for that role. The verdict is simple: pick the FirePro W600 for desktop compute and multi-output work, pick the 8790M only if Vulkan performance or a mobile form factor is the priority.

Where Each One Wins

The AMD FirePro W600 wins decisively in OpenCL compute. Its 6223 score against the 8790M’s 5017 is a 24% margin, and its average benchmark score is higher by over 500 points. The FirePro also wins on architectural throughput: it has 512 shading units versus 384, 32 texture units versus 24, and 16 ROPs versus 8. This translates to a pixel rate of 12.00 GPixel/s against the 8790M’s 7.200 GPixel/s, and a texture rate of 24.00 GTexel/s against 21.60 GTexel/s. FP32 compute is 768.0 GFLOPS versus 691.2 GFLOPS, a 11% advantage that aligns with the benchmark delta.

The Radeon HD 8790M wins in the Vulkan API, where it scores 6365. This is a significant result because it outpaces the FirePro W600’s best recorded score by 142 points. While the FirePro has no Vulkan benchmark in the database, the 8790M’s Vulkan performance demonstrates that its GCN 1.0 architecture can still deliver competitive results in newer APIs, at least in this specific test. The 8790M also has a higher boost clock of 900 MHz compared to its base of 850 MHz, which is a detail the FirePro lacks entirely, as the W600 has no recorded base or boost clocks.

The FirePro W600 also wins on connectivity and form factor. It offers 6x mini-DisplayPort 1.2 outputs, a single-slot width, and no power connectors, making it an easy addition to a workstation chassis. The 8790M is an MXM module with a bus interface of MXM-A (3.0), which means it is intended for laptops or compact systems where the display outputs are dependent on the host device. The FirePro’s PCIe 3.0 x16 interface is also a standard desktop slot, while the 8790M’s MXM interface is not user-upgradeable in the same way.

In terms of memory, both cards have 2 GB of GDDR5 on a 128-bit bus with 64.00 GB/s bandwidth, so that is a tie. The 8790M’s memory clock is 1000 MHz with 4 Gbps effective, matching the FirePro’s identical memory clock and effective rate. Neither card offers any ray tracing or tensor cores, and both support DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The AMD FirePro W600, with a score of 6223 in Geekbench OpenCL, which is 24% higher than the AMD Radeon HD 8790M’s score of 5017.

Q: Does the Radeon HD 8790M outperform the FirePro W600 in any benchmark?

A: Yes, the 8790M records a Geekbench Vulkan score of 6365, which is higher than the FirePro W600’s OpenCL score of 6223. The FirePro W600 has no recorded Vulkan benchmark, so this is the only test where the 8790M shows a higher raw number.

Q: How do these GPUs compare to their nearest rivals?

A: The FirePro W600’s average score of 6223 is 0.2% above the AMD Radeon HD 6950 (6210) and 0.7% below the NVIDIA GeForce RTX 4070 Ti SUPER AD102 and RTX 5070 Ti SUPER (both 6270). The 8790M’s average score of 5691 is 0.4% below the Intel Iris Pro Graphics P6300 (5712) and 1.6% above the NVIDIA Quadro M500M (5604).

Q: What are the key architectural differences between the two chips?

A: Both use GCN 1.0 architecture and a 28 nm TSMC process, but the FirePro W600 uses the Cape Verde chip with 1,500 million transistors on a 123 mm² die, while the 8790M uses the Mars chip with 950 million transistors on a 77 mm² die. The FirePro has 512 shading units, 32 TMUs, and 16 ROPs; the 8790M has 384 shading units, 24 TMUs, and 8 ROPs.

Q: Which GPU has higher pixel and texture rates?

A: The FirePro W600 has a pixel rate of 12.00 GPixel/s and a texture rate of 24.00 GTexel/s, both higher than the 8790M’s 7.200 GPixel/s and 21.60 GTexel/s.

Q: Do both GPUs support the same APIs?

A: Yes, both support DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Neither has ray tracing or tensor cores.

Architecture Differences

The two GPUs share the same GCN 1.0 architecture and are both built by TSMC on a 28 nm process, but the underlying chips differ significantly. The FirePro W600 uses the Cape Verde chip, which contains 1,500 million transistors on a 123 mm² die, yielding a transistor density of 12.2M per mm². The Radeon HD 8790M uses the Mars chip, with 950 million transistors on a 77 mm² die, for a density of 12.3M per mm². The density is nearly identical, but the FirePro’s larger die allows for more execution resources.

The FirePro W600 has 512 shading units, 32 texture mapping units, and 16 render output units. The 8790M has 384 shading units, 24 TMUs, and only 8 ROPs. This is a 33% advantage in shading units for the FirePro, a 33% advantage in TMUs, and a 100% advantage in ROPs. The ROP difference is particularly impactful for pixel fill rate, which explains why the FirePro’s 12.00 GPixel/s more than doubles the 8790M’s 7.200 GPixel/s. The texture rate difference is smaller but still favors the FirePro: 24.00 GTexel/s versus 21.60 GTexel/s, a 11% gap.

FP32 compute performance follows the same pattern. The FirePro W600 delivers 768.0 GFLOPS, while the 8790M delivers 691.2 GFLOPS. The delta is about 11%, which is smaller than the shader count difference suggests because the 8790M can boost its clock to 900 MHz, while the FirePro has no recorded boost clock. The 8790M’s base clock is 850 MHz, and its boost is 900 MHz, a 5.9% increase. The FirePro’s clocks are not listed in the database, so a direct clock comparison is impossible, but the recorded throughput values already account for any clock differences.

Memory architecture is identical: both have 2 GB of GDDR5 on a 128-bit bus with a 64.00 GB/s bandwidth and a 1000 MHz memory clock (4 Gbps effective). This means the memory subsystem does not differentiate the two. The differences are purely in the compute and rasterization pipelines.

The FirePro W600 is a desktop card with a PCIe 3.0 x16 interface, a single-slot width, and no power connectors. The 8790M is an MXM module with an MXM-A (3.0) bus interface, which is designed for mobile systems. The FirePro’s display outputs are 6x mini-DisplayPort 1.2, while the 8790M’s outputs are listed as portable device dependent, meaning they rely on the host laptop. The FirePro’s TDP is 75 W with a suggested PSU of 250 W, while the 8790M’s TDP is not recorded.

Specification Differences

The following fields differ between the AMD FirePro W600 and the AMD Radeon HD 8790M:

• Chip: Cape Verde (FirePro W600) versus Mars (Radeon HD 8790M)
• Generation: FirePro GCN (Wx000) versus Solar System (HD 8700M)
• Transistors: 1,500 million versus 950 million
• Die Size: 123 mm² versus 77 mm²
• Transistor Density: 12.2M / mm² versus 12.3M / mm²
• Base Clock: Not recorded versus 850 MHz
• Boost Clock: Not recorded versus 900 MHz
• Shading Units: 512 versus 384
• TMUs: 32 versus 24
• ROPs: 16 versus 8
• Pixel Rate: 12.00 GPixel/s versus 7.200 GPixel/s
• Texture Rate: 24.00 GTexel/s versus 21.60 GTexel/s
• FP32: 768.0 GFLOPS versus 691.2 GFLOPS
• TDP: 75 W versus not recorded
• Slot Width: Single-slot versus MXM Module
• Suggested PSU: 250 W versus not recorded
• Bus Interface: PCIe 3.0 x16 versus MXM-A (3.0)
• Display Outputs: 6x mini-DisplayPort 1.2 versus Portable Device Dependent
• Dimensions: 168 mm (6.6 inches) length, 111 mm (4.4 inches) height, 20 mm (0.8 inches) width versus not recorded
• Release Date: 2012-06-12 versus 2013-03-31
• Predecessor: FirePro Terascale versus London
• Successor: Radeon Pro Polaris versus Gem System
• Launch MSRP: 599 USD versus not recorded

Both GPUs share the same memory size, type, bus width, bandwidth, memory clock, API support, foundry, process node, and architecture. Neither has ray tracing or tensor cores. Both are end-of-life products.