AMD Radeon Pro 455 vs AMD Radeon RX 6600S Comparison

# AMD Radeon Pro 455 vs AMD Radeon RX 6600S

The AMD Radeon Pro 455 and AMD Radeon RX 6600S represent two distinct eras of mobile graphics from the same manufacturer. The Pro 455, built on GCN 4.0 with the Baffin chip, was designed for professional Mac systems in late 2016. The RX 6600S, using RDNA 2.0 with the Navi 23 chip, arrived in early 2022 as part of the RX 6000M mobile lineup. The database records only one shared benchmark between them, Geekbench OpenCL, where the RX 6600S delivers a score of 66435 against the Pro 455's 10336, a difference of 84.4% in favor of the newer part. Despite that gap, the Pro 455 holds a higher overall percentile ranking at 52 versus the RX 6600S's 49, which reflects how different benchmark suites weight their results. The following analysis breaks down where each GPU wins, how their architectures diverge, and what the recorded data implies for real-world usage.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon Pro 455 has an average benchmark score of 12831, while the AMD Radeon RX 6600S records 10629. This places the Pro 455 in the 52nd percentile among all GPUs, whereas the RX 6600S sits in the 49th percentile.

Q: How do the two compare in the single shared benchmark?

A: In Geekbench OpenCL, the RX 6600S scores 66435 compared to the Pro 455's 10336. The RX 6600S wins this test by 84.4%, a massive margin that reflects its much newer architecture and higher compute throughput.

Q: What memory configurations do they use?

A: The Pro 455 uses 2 GB of GDDR5 memory on a 128-bit bus with 81.28 GB/s bandwidth. The RX 6600S uses 4 GB of GDDR6 memory on the same 128-bit bus but achieves 224.0 GB/s bandwidth, nearly three times the Pro 455's memory throughput.

Q: Do both support ray tracing?

A: No. The RX 6600S includes 28 ray tracing cores as part of its RDNA 2.0 architecture, while the Pro 455, based on GCN 4.0, has no ray tracing cores listed in the database.

Q: What are their thermal design power ratings?

A: The Pro 455 has a TDP of 35 W and uses an MXM module slot. The RX 6600S has a TDP of 80 W and is classified as an IGP (integrated graphics processor) form factor.

Q: Which GPU has better DirectX support?

A: The RX 6600S supports DirectX 12 Ultimate (12_2), while the Pro 455 supports DirectX 12 (12_0). The RX 6600S also supports Vulkan 1.4 versus Vulkan 1.3 on the Pro 455.

Where Each One Wins

The RX 6600S wins decisively in raw compute performance. Its Geekbench OpenCL score of 66435 dwarfs the Pro 455's 10336, a 84.4% advantage. This translates to superiority in any workload that leverages general-purpose GPU computing, such as rendering, simulation, or data processing tasks that scale with shading units and memory bandwidth. The RX 6600S also holds advantages in pixel rate (128.0 GPixel/s versus 13.68 GPixel/s), texture rate (224.0 GTexel/s versus 41.04 GTexel/s), and FP32 throughput (7.168 TFLOPS versus 1,313.3 GFLOPS). For modern gaming or content creation, the RX 6600S is the clear performer.

The Pro 455 wins in the overall percentile ranking and average benchmark score. With an average of 12831 and 52nd percentile placement, it outperforms the RX 6600S's 10629 average and 49th percentile. This suggests that in certain legacy benchmarks or driver-optimized professional workloads, the Pro 455 maintains competitive standing. Its nearest rivals in the database include the NVIDIA GeForce GTX 590 (average 12830, 0% difference), AMD FirePro W5100 (12847, -0.1%), and AMD Radeon 740M (12870, -0.3%). The RX 6600S, by contrast, sits near the NVIDIA GeForce GTX 560 Ti (10690, -0.6%) and AMD Radeon R9 M275X (10582, 0.4%). The Pro 455's higher average likely stems from its inclusion in benchmark suites that favor its specific feature set or driver maturity in Mac environments.

Architecture Differences

The architectural gap between these two GPUs is generational. The Pro 455 uses GCN 4.0, built on a 14 nm process at GlobalFoundries with 3,000 million transistors on a 123 mm² die. The RX 6600S uses RDNA 2.0, fabricated on a 7 nm process at TSMC with 11,060 million transistors on a 237 mm² die. The transistor density jumps from 24.4M per mm² to 46.7M per mm², showing how much more densely packed the newer process is.

The compute layout differs significantly. The Pro 455 has 768 shading units, 48 texture mapping units, and 16 raster operation pipelines. The RX 6600S has 1792 shading units, 112 TMUs, and 64 ROPs. That is more than double the shading units and quadruple the ROPs. The RX 6600S also introduces 28 ray tracing cores, a feature entirely absent from the GCN 4.0 design. The FP16 performance ratio changes as well: the Pro 455 runs FP16 at 1:1 with FP32 (both at 1,313.3 GFLOPS), while the RX 6600S runs FP16 at 2:1, reaching 14.34 TFLOPS versus 7.168 TFLOPS for FP32. This makes the RX 6600S significantly faster for workloads that can use half-precision math.

Memory architecture also reflects the newer design. Both use a 128-bit bus, but the RX 6600S pairs it with GDDR6 at 14 Gbps effective, yielding 224.0 GB/s, while the Pro 455 uses GDDR5 at 5.1 Gbps effective for 81.28 GB/s. The RX 6600S also supports PCIe 4.0 x8, double the bandwidth of the Pro 455's PCIe 3.0 x8 interface. The Pro 455's memory clock is listed only as 1270 MHz with 5.1 Gbps effective, while the RX 6600S lists a base clock of 1700 MHz, boost of 2000 MHz, and game clock of 1881 MHz.

Specification Differences

The two GPUs differ across nearly every specification field. The process node moves from 14 nm (GlobalFoundries) to 7 nm (TSMC). Transistor count rises from 3,000 million to 11,060 million, and die size grows from 123 mm² to 237 mm², while transistor density improves from 24.4M/mm² to 46.7M/mm². The RX 6600S has explicit clock speeds (base 1700 MHz, boost 2000 MHz, game 1881 MHz, memory 1750 MHz at 14 Gbps effective), whereas the Pro 455 only lists memory clock at 1270 MHz and 5.1 Gbps effective, with no base or boost figures recorded.

Memory capacity doubles from 2 GB GDDR5 to 4 GB GDDR6, with bandwidth rising from 81.28 GB/s to 224.0 GB/s. Shading units increase from 768 to 1792, TMUs from 48 to 112, ROPs from 16 to 64, and the RX 6600S adds 28 ray tracing cores. Pixel rate jumps from 13.68 GPixel/s to 128.0 GPixel/s, texture rate from 41.04 GTexel/s to 224.0 GTexel/s, and FP32 from 1,313.3 GFLOPS to 7.168 TFLOPS. FP16 scales from 1,313.3 GFLOPS (1:1 ratio) to 14.34 TFLOPS (2:1 ratio).

TDP rises from 35 W to 80 W. The Pro 455 uses an MXM module slot, while the RX 6600S is classified as an IGP. Both have no power connectors and portable-device-dependent display outputs. The bus interface upgrades from PCIe 3.0 x8 to PCIe 4.0 x8. DirectX support moves from 12 (12_0) to 12 Ultimate (12_2), Vulkan from 1.3 to 1.4, and OpenGL remains at 4.6 for both. The Pro 455 belongs to the Radeon Pro Mac (400 Series) generation, while the RX 6600S belongs to the Navi Mobile (RX 6000M) generation. Production status for both is end-of-life, with release dates of late 2016 and early 2022 respectively.

Head-to-Head Benchmarks

The database records exactly one head-to-head benchmark between these two GPUs: Geekbench OpenCL. The Pro 455 scores 10336, and the RX 6600S scores 66435. The delta percentage is -84.4%, meaning the Pro 455 achieves only 15.6% of the RX 6600S's score. This is not a marginal improvement; it is a complete generational leap. The RX 6600S's advantage comes from having 1792 shading units versus 768, a 2.33x increase, combined with 224.0 GB/s memory bandwidth versus 81.28 GB/s, a 2.76x increase, and a much higher clock ceiling.

The Pro 455's overall average benchmark score of 12831, however, beats the RX 6600S's 10629. This apparent contradiction resolves when considering that the Pro 455's average comes from three Geekbench tests (Metal, OpenCL, Vulkan) while the RX 6600S's average includes Passmark tests (DirectX 9, 10, 11, 12, G2D, G3D, GPU compute) plus Geekbench OpenCL. The RX 6600S's Passmark DirectX scores are low (81 for DirectX 10, 105 for DirectX 11, 56 for DirectX 12, 176 for DirectX 9), which drags its average down despite the strong OpenCL result. Its Passmark G3D score of 12649 and GPU compute score of 4879 are more respectable but still lower than the Pro 455's Geekbench Metal score of 15916.

In terms of nearest rivals, the Pro 455 sits within 0.5% of the NVIDIA GeForce GTX 670, 0% of the GTX 590, -0.1% of the AMD FirePro W5100, and -0.3% of the AMD Radeon 740M. The RX 6600S sits within 1.4% of the AMD Radeon RX 550X, 0.4% of the AMD Radeon R9 M275X, -0.6% of the NVIDIA GeForce GTX 560 Ti, and -1.2% of the NVIDIA Quadro K2200. These rival clusters show that the Pro 455 competes with mid-range desktop GPUs from 2012-2013 era, while the RX 6600S, despite its modern architecture, falls into a similar performance bracket in the aggregate database due to its mixed benchmark results.

The Verdict

The data points to a clear split. For raw compute performance, the AMD Radeon RX 6600S is the definitive winner. Its Geekbench OpenCL score of 66435 versus 10336 leaves no ambiguity: it is 84.4% faster in that workload. The RX 6600S also offers double the memory (4 GB versus 2 GB), nearly triple the bandwidth (224.0 GB/s versus 81.28 GB/s), more than double the shading units (1792 versus 768), and exclusive ray tracing support. Anyone running modern games, GPU compute tasks, or applications that benefit from FP16 throughput should choose the RX 6600S.

The AMD Radeon Pro 455, however, holds its own in the aggregate database. Its average benchmark score of 12831 places it in the 52nd percentile, above the RX 6600S's 49th percentile. Its Geekbench Metal score of 15916 and Vulkan score of 12240 indicate strong performance in Apple-centric or cross-platform APIs, likely due to its design for Mac systems. The Pro 455's nearest rivals include the GTX 590 and FirePro W5100, both within 0.1% of its average score, showing that it remains competitive within its niche despite being end-of-life.

The choice depends on the workload. For legacy professional Mac applications that use Metal or OpenCL in specific ways, the Pro 455 may still deliver adequate results. For any modern workload, particularly those leveraging DirectX 12 Ultimate, ray tracing, or high-bandwidth memory, the RX 6600S is the only rational pick. The 84.4% OpenCL gap is the single most telling number in this comparison, and it favors the newer GPU overwhelmingly. The Pro 455's higher percentile ranking reflects benchmark selection bias rather than actual performance superiority, as its best scores come from tests where the RX 6600S has no recorded equivalent. Users should prioritize the RX 6600S for compute-intensive tasks and the Pro 455 only if specific software compatibility demands it.