AMD FirePro W5170M vs AMD Radeon RX 6600S Comparison

Where Each One Wins

The recorded data splits these two mobile GPUs cleanly along generational lines. The AMD Radeon RX 6600S wins the only shared benchmark, Geekbench OpenCL, by an enormous margin. Its score of 66,435 versus 8,140 for the FirePro W5170M represents a 716.2% delta, which is not a marginal improvement but a complete class separation. If the workload relies on OpenCL compute, the RX 6600S is the only rational choice from this pairing.

The AMD FirePro W5170M has no benchmark wins in the head-to-head data. It does, however, hold a separate Geekbench Vulkan score of 9,050 which the RX 6600S does not have recorded in the database. That does not constitute a win in a direct comparison, but it does show the older card has some functional capability in Vulkan workloads. For everything else, the RX 6600S dominates.

The use-case split is therefore simple. The RX 6600S is for anyone who needs modern compute performance, DX12-era features, and high throughput in OpenCL. The FirePro W5170M is for legacy compatibility scenarios, where the workload specifically requires a GCN 1.0 part or where Vulkan support at version 1.2.170 is sufficient. For raw speed and modern API support, the RX 6600S wins outright.

Architecture Differences

The two chips come from entirely different design eras within AMD. The Radeon RX 6600S uses the Navi 23 chip built on RDNA 2.0 architecture, fabricated on a 7 nm TSMC process. The FirePro W5170M uses the Tropo chip built on GCN 1.0 architecture, fabricated on a 28 nm TSMC process. That process gap alone explains much of the performance difference. The RX 6600S packs 11,060 million transistors into a 237 mm² die, giving a transistor density of 46.7 million per square millimeter. The FirePro W5170M has 1,500 million transistors on a 123 mm² die, for a density of 12.2 million per square millimeter. The newer chip crams over three times the transistor density into roughly twice the die area.

Shading resources differ drastically. The RX 6600S has 1,792 shading units, 112 texture mapping units, and 64 render output units. It also includes 28 ray tracing cores, a feature the FirePro W5170M lacks entirely. The older card has 640 shading units, 40 TMUs, and only 16 ROPs. The RX 6600S has no tensor cores listed, and neither does the FirePro, so that field is not a differentiator here.

The architecture generation gap also shows in API support. The RX 6600S supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The FirePro W5170M supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Both have OpenGL 4.6, but the DirectX and Vulkan feature levels put the RX 6600S in a much newer compatibility class. The FirePro is a GCN 1.0 design from the FirePro Mobile Wx100M generation, while the RX 6600S comes from the Navi Mobile RX 6000M generation. The predecessor and successor relationships also differ: the RX 6600S follows Polaris Mobile, and the FirePro W5170M follows FirePro Mobility and was succeeded by Radeon Pro Mobile.

Head-to-Head Benchmarks

The only direct benchmark recorded in the head-to-head set is Geekbench OpenCL. The RX 6600S scores 66,435, and the FirePro W5170M scores 8,140. The delta is 716.2% in favor of the RX 6600S. To put that in perspective, the RX 6600S is roughly eight times faster in this compute test. That is not a close contest by any reasonable interpretation.

Looking at the broader database averages, the RX 6600S has an average benchmark score of 10,629 across all its recorded tests, while the FirePro W5170M averages 8,595. The RX 6600S also sits at the 49th percentile among all GPUs, versus the 44th percentile for the FirePro. Those percentile figures are close in rank terms, but the average score gap of over 2,000 points reflects the different test suites each card has recorded. The RX 6600S has more entries in the database, including Passmark tests for DirectX 9, 10, 11, 12, G2D, G3D, and GPU compute. The FirePro W5170M only has Geekbench OpenCL and Vulkan entries.

The nearest rivals for each card reinforce the generational gap. The RX 6600S sits within 1.4% of cards like the AMD Radeon R9 M275X and the NVIDIA GeForce GTX 560 Ti, with an average score delta of +0.4% versus the R9 M275X and -0.6% versus the GTX 560 Ti. The FirePro W5170M is within 1.6% of the Intel Arc A380, the NVIDIA Quadro P2200, the AMD Radeon HD 8870M, and the NVIDIA GeForce MX330. Neither card is a performance outlier among its peers, but the RX 6600S sits in a faster peer group overall.

The Passmark results for the RX 6600S show where its strengths lie. Its best relative scores are in Passmark G3D at 12,649 and Passmark GPU Compute at 4,879. DirectX 9 scores 176, DirectX 11 scores 105, and DirectX 10 scores 81. DirectX 12 is the weakest at 56, which is unusual but reflects the specific driver and workload behavior in that test. The FirePro has no Passmark data recorded, so a direct comparison across those subtests is not possible.

Specification Differences

The two cards differ in nearly every measurable specification. The RX 6600S has 4 GB of GDDR6 memory on a 128 bit bus, delivering 224.0 GB/s of bandwidth. The FirePro W5170M has 2 GB of GDDR5 memory on the same 128 bit bus, but only 72.00 GB/s of bandwidth. The memory clock difference is stark: the RX 6600S runs at 1750 MHz with 14 Gbps effective, while the FirePro runs at 1125 MHz with 4.5 Gbps effective.

Clock speeds also favor the newer card heavily. The RX 6600S has a base clock of 1700 MHz, a boost clock of 2000 MHz, and a game clock of 1881 MHz. The FirePro W5170M has a base clock of 900 MHz and a boost clock of 925 MHz, with no game clock listed. That is roughly a doubling of clock speed across the board.

Compute throughput follows the same pattern. The RX 6600S delivers 7.168 TFLOPS FP32 and 14.34 TFLOPS FP16 at a 2:1 ratio. The FirePro W5170M delivers 1,184.0 GFLOPS FP32, which is about 1.184 TFLOPS, and has no FP16 figure listed. Pixel and texture rates also diverge: the RX 6600S has 128.0 GPixel/s and 224.0 GTexel/s, while the FirePro has 14.80 GPixel/s and 37.00 GTexel/s.

The RX 6600S has a TDP of 80 W and is an integrated GPU package (IGP) with no power connectors, using a PCIe 4.0 x8 interface. The FirePro W5170M has no TDP listed, is an MXM Module with no power connectors, and uses an MXM-A (3.0) bus interface. Both are marked end-of-life, with the RX 6600S released on 2022-01-03 and the FirePro W5170M released on 2014-08-24. Neither has a launch MSRP in the database. Display outputs for both are listed as portable device dependent.

FAQ

Q: Which GPU is faster in OpenCL compute?

A: The AMD Radeon RX 6600S scores 66,435 in Geekbench OpenCL, compared to 8,140 for the FirePro W5170M, a 716.2% advantage.

Q: Does the FirePro W5170M support Vulkan?

A: Yes, it supports Vulkan 1.2.170, and it has a recorded Geekbench Vulkan score of 9,050. The RX 6600S supports Vulkan 1.4, but has no Geekbench Vulkan score in the database.

Q: What memory configuration does each card use?

A: The RX 6600S has 4 GB of GDDR6 on a 128 bit bus with 224.0 GB/s bandwidth. The FirePro W5170M has 2 GB of GDDR5 on a 128 bit bus with 72.00 GB/s bandwidth.

Q: Do both cards support DirectX 12?

A: Both do, but at different levels. The RX 6600S supports DirectX 12 Ultimate (12_2), while the FirePro W5170M supports DirectX 12 (11_1).

Q: Which card has ray tracing cores?

A: Only the RX 6600S has ray tracing cores, with 28 listed. The FirePro W5170M has none.

Q: What is the transistor density difference?

A: The RX 6600S has 46.7 million transistors per square millimeter on a 7 nm process. The FirePro W5170M has 12.2 million per square millimeter on a 28 nm process.

The Verdict

The data points to one answer for almost every modern workload: the AMD Radeon RX 6600S. It is faster in the only shared benchmark by a factor of eight, has more memory, higher bandwidth, newer architecture, and better API support. The 716.2% OpenCL lead is the single most decisive number in this comparison. Anyone running compute tasks, modern games, or DirectX 12 Ultimate workloads should choose the RX 6600S without hesitation.

The AMD FirePro W5170M has a narrower case. It is a GCN 1.0 part with a recorded Vulkan score, which may matter for legacy software that specifically targets that architecture generation. Its average benchmark score of 8,595 and 44th percentile ranking place it in a lower performance tier, close to the Intel Arc A380 and NVIDIA GeForce MX330. If the workload is ancient, Vulkan-only, or requires an MXM module form factor, the FirePro W5170M is the only one of the two that fits. Otherwise, the RX 6600S is the clear pick from the recorded data.