AMD Ryzen Threadripper PRO 9955WX vs Intel Xeon 654 Comparison

The AMD Ryzen Threadripper PRO 9955WX and the Intel Xeon 654 represent two distinct approaches to high-end workstation computing. The recorded data shows the AMD processor as the dominant performer in the majority of benchmarks, winning 14 of the 17 head-to-head tests, while the Intel Xeon 654 counters with a few specific workload advantages. The AMD Ryzen Threadripper PRO 9955WX, built on the Zen 5 architecture, combines a high base clock of 4.50 GHz with a boost clock of 5.40 GHz, whereas the Intel Xeon 654, using Granite Rapids architecture, operates at a base clock of 3.10 GHz and boosts to 4.80 GHz. These differences translate into measurable performance gaps across rendering, encryption, and math workloads, with the Intel part taking the lead only in prime number finding, floating-point math, and physics simulations.

FAQ

Q: Which processor has a higher overall average benchmark score?

A: The AMD Ryzen Threadripper PRO 9955WX records an average benchmark score of 101041, which is significantly higher than the Intel Xeon 654's average score of 90717. The database places the AMD part in the 97th percentile of all CPUs, while the Intel Xeon 654 sits in the 96th percentile.

Q: What is the performance difference in single-core Cinebench R23?

A: The AMD Ryzen Threadripper PRO 9955WX scores 8399 in Cinebench R23 single-core, while the Intel Xeon 654 scores 7362. This gives the AMD processor a 14.1% advantage in that specific test.

Q: Does the Intel Xeon 654 beat the AMD processor in any benchmarks?

A: Yes, the Intel Xeon 654 wins in three recorded tests: PassMark find prime numbers (390 versus 337, a 13.6% advantage), PassMark floating-point math (163093 versus 156215, a 4.2% advantage), and PassMark physics (5596 versus 4156, a 25.7% advantage).

Q: How do the two processors compare in memory bandwidth?

A: Both processors support DDR5 memory with an eight-channel memory bus, and each records a memory bandwidth of 409.6 GB/s. Neither holds an advantage in this specification.

Q: What are the core and thread counts for each processor?

A: The Intel Xeon 654 has 18 cores and 36 threads, while the AMD Ryzen Threadripper PRO 9955WX has 16 cores and 32 threads. Despite having fewer cores and threads, the AMD processor wins the majority of multi-threaded benchmarks.

Q: Which processor has a higher boost clock?

A: The AMD Ryzen Threadripper PRO 9955WX has a boost clock of 5.40 GHz, which is higher than the Intel Xeon 654's boost clock of 4.80 GHz. The AMD part also has a higher base clock at 4.50 GHz compared to 3.10 GHz.

Architecture Differences

The AMD Ryzen Threadripper PRO 9955WX belongs to the 9000 series and uses the Zen 5 architecture, codenamed Shimada Peak, while the Intel Xeon 654 is based on Granite Rapids architecture. The manufacturing processes differ substantially: the AMD processor is built on a 4 nm process by TSMC, whereas the Intel Xeon 654 uses a 5 nm process from Intel's own foundry. The die sizes also reflect this difference, with the AMD part measuring 2x 70.6 mm² and the Intel part measuring 2x 598 mm², though the Intel die is larger while hosting more cores.

Cache hierarchies diverge between the two designs. The AMD Ryzen Threadripper PRO 9955WX features 64 KB of L1 cache per core, 1 MB of L2 cache per core, and 64 MB of shared L3 cache. The Intel Xeon 654 offers 112 KB of L1 cache per core, 2 MB of L2 cache per core, and 72 MB of shared L3 cache. This gives the Intel processor a larger total cache footprint, but the benchmark data indicates that the AMD processor's architectural efficiency compensates for its smaller cache capacity.

Memory support is identical on paper: both use DDR5 with an eight-channel memory bus and 409.6 GB/s of bandwidth, and both support ECC memory. PCIe capabilities also match, with both providing Gen 5 and 128 lanes from the CPU only. The AMD processor is classified as a desktop market segment part, while the Intel Xeon 654 is categorized as a server or workstation segment part. Both have unlocked multipliers and are currently in active production.

Head-to-Head Benchmarks

The AMD Ryzen Threadripper PRO 9955WX demonstrates consistent superiority in rendering workloads. In Cinebench R15 multicore, the AMD part scores 5996 against the Intel Xeon 654's 5256, a 14.1% advantage. The same margin appears in Cinebench R20 multicore, where the AMD scores 24987 versus 21903, and in Cinebench R23 multicore, where the AMD scores 59494 versus 52150, both at 14.1% deltas. Single-core rendering follows the same pattern: Cinebench R15 single-core shows the AMD at 846 versus 742 (14% delta), Cinebench R20 single-core shows 3527 versus 3092 (14.1% delta), and Cinebench R23 single-core shows 8399 versus 7362 (14.1% delta). These consistent margins suggest a stable architectural advantage for the AMD processor across Cinebench versions.

In PassMark workloads, the AMD processor records its largest wins in extended instructions and random string sorting. For extended instructions, the AMD scores 76363 against 63539, a 20.2% lead. Random string sorting shows a similar gap, with the AMD at 99813 versus 82828, a 20.5% advantage. Single-thread performance also favors the AMD part, with a score of 4530 versus 3778, a 19.9% delta. Data compression shows a 12.5% lead for the AMD (920954 versus 818902), and data encryption shows a 9.1% lead (44389 versus 40675). Integer math favors the AMD at 236120 versus 207745, a 13.7% delta, and the multithread test shows the AMD at 67035 versus 61353, a 9.3% advantage.

The Intel Xeon 654 captures three benchmark wins, each with a distinct character. The largest Intel win is in PassMark physics, where it scores 5596 against the AMD's 4156, a 25.7% advantage. This is the most substantial delta in either direction across all recorded tests. In PassMark floating-point math, the Intel scores 163093 versus 156215, a 4.2% lead. Finally, in PassMark find prime numbers, the Intel scores 390 versus 337, a 13.6% advantage. These wins suggest that the Intel Xeon 654 has specific strengths in physics simulation and floating-point operations, despite losing the broader multithread and single-thread tests.

Specification Differences

The AMD Ryzen Threadripper PRO 9955WX has 16 cores and 32 threads, while the Intel Xeon 654 has 18 cores and 36 threads. The base clock differs by 1.40 GHz, with the AMD at 4.50 GHz and the Intel at 3.10 GHz. The boost clock difference is 0.60 GHz, with the AMD at 5.40 GHz and the Intel at 4.80 GHz. The TDP also differs, with the AMD rated at 350 watts and the Intel at 200 watts.

Process node and foundry differ: the AMD uses a 4 nm process from TSMC, while the Intel uses a 5 nm process from Intel. The die size is 2x 70.6 mm² for the AMD and 2x 598 mm² for the Intel. Cache configurations differ across all levels: the AMD has 64 KB of L1 per core, 1 MB of L2 per core, and 64 MB of L3, while the Intel has 112 KB of L1 per core, 2 MB of L2 per core, and 72 MB of L3. The release dates differ, with the AMD launching on 2025-07-22 and the Intel on 2026-02-01. The launch MSRP for the AMD is $1649, and for the Intel it is $1199. The market segments also differ, with the AMD classified as Desktop and the Intel as Server/Workstation. The part numbers are 100-000000725 for the AMD and SA2DP for the Intel.

The Verdict

The benchmark data clearly positions the AMD Ryzen Threadripper PRO 9955WX as the stronger overall performer. With an average benchmark score of 101041 versus 90717, the AMD processor leads by approximately 10.2% in the database's aggregated metric. It wins 14 of the 17 head-to-head tests, including all six Cinebench tests and the majority of PassMark workloads. The AMD part also ranks higher in the percentile distribution, at 97 compared to 96 for the Intel Xeon 654.

The Intel Xeon 654, despite having more cores and threads, loses most multi-threaded tests. Its 18 cores and 36 threads do not translate into wins in Cinebench multicore or PassMark multithread, where the AMD processor with 16 cores and 32 threads prevails by margins of 9.3% to 14.1%. This indicates that the AMD Zen 5 architecture delivers higher per-core throughput, which is consistent with its significantly higher base and boost clocks.

For users who prioritize physics simulation, floating-point math, and prime number finding, the Intel Xeon 654 offers specific advantages. Its 25.7% win in PassMark physics is the largest margin in any test, and its floating-point math win, while narrower at 4.2%, indicates a genuine strength. These wins suggest that the Intel part may excel in workloads that depend on floating-point throughput and physics calculations.

However, for the broader range of workstation tasks, including rendering, compression, encryption, string sorting, and general multithreaded operations, the AMD Ryzen Threadripper PRO 9955WX is the better choice based on the recorded data. The AMD processor also leads in single-thread performance by 19.9%, which is critical for applications that rely on per-core speed. The verdict from the data is clear: the AMD part is the superior general-purpose workstation processor, while the Intel part has niche strengths in specific computational domains.

Where Each One Wins

The AMD Ryzen Threadripper PRO 9955WX dominates rendering and content creation workloads. In all Cinebench tests, the AMD processor leads by approximately 14%, covering both single-core and multi-core scenarios. This makes it the stronger choice for 3D rendering, video encoding, and other tasks that rely on Cinebench-style performance. The AMD part also wins in data compression (12.5% lead), data encryption (9.1% lead), and random string sorting (20.5% lead), which are common in file archiving, secure data handling, and database operations. For integer math, the AMD leads by 13.7%, and for extended instructions, it leads by 20.2%, making it preferable for software development and scientific computing that uses SIMD instructions. Single-thread performance favors the AMD by 19.9%, so applications that are not well-parallelized will run faster on the AMD processor.

The Intel Xeon 654 wins in three specific areas. PassMark physics shows a 25.7% advantage for the Intel part, indicating that physics simulation workloads, such as those in engineering or scientific analysis, will perform notably better on this processor. Floating-point math favors the Intel by 4.2%, so tasks that involve heavy floating-point calculations, such as certain numerical simulations or financial modeling, may benefit from the Intel architecture. Prime number finding shows a 13.6% lead for the Intel, which is relevant for cryptography and number theory applications. For users whose primary workloads align with these three areas, the Intel Xeon 654 offers measurable benefits. For all other benchmarked workloads, the AMD Ryzen Threadripper PRO 9955WX provides the higher performance, making it the recommended choice for most workstation and desktop computing scenarios.