AMD Ryzen 5 PRO 9645 vs Intel Xeon 636 Comparison

Head-to-Head Benchmarks

The benchmark data presents a clear split between these two processors. The Intel Xeon 636 wins 9 of the 11 recorded head-to-head comparisons, while the AMD Ryzen 5 PRO 9645 takes the remaining 2. The margins, however, tell a more nuanced story than the win count alone.

The largest victory for the Intel Xeon 636 comes in the PassMark physics test, where it scores 3645 against the AMD's 1945, a delta of 87.4%. This is a dominant result, nearly doubling the AMD part's output in that workload. Floating point math also heavily favors Intel, with a score of 107826 versus 62720, a 71.9% advantage. Encryption is another strong area for Intel, posting 27193 against 17599, a 54.5% lead.

Compression and integer workloads show consistent, though slightly smaller, Intel advantages. Data compression sees Intel at 550395 versus AMD's 363736, a 51.3% gap. Integer math favors Intel by 48.7%, with scores of 138281 and 93019 respectively. Extended instructions go Intel's way by 45.7%, at 43282 versus 29705.

Multi-threaded performance, often a key differentiator for workstation parts, shows Intel ahead by 41.3% with a score of 44421 against 31434. Random string sorting follows a similar pattern, Intel winning 54420 to 38410, a 41.7% margin. Even the closest Intel win, find prime numbers, goes to the Xeon 636 by 8.5%, scoring 255 versus 235.

The AMD Ryzen 5 PRO 9645's victories are concentrated entirely in single-thread performance. In the PassMark single thread test, AMD scores 4636 against Intel's 3937, a 15.1% advantage. This is a meaningful edge for lightly threaded workloads, but it stands alone against a broad Intel sweep elsewhere.

Context from the database's nearest rival comparisons helps frame these results. The Intel Xeon 636 posts an average benchmark score of 61360, placing it within 0.6% of the Intel Core i9-13900T and 0.7% of the Core i9-13900K. The AMD Ryzen 5 PRO 9645 averages 58916, which is 0.2% ahead of the AMD Ryzen AI 9 HX 470 and 0.7% ahead of the Intel Xeon w5-2545. Both chips sit at the 92nd percentile among all CPUs in the database, indicating they are both high performers, but the Intel part holds a lead in overall average score of roughly 4.1%.

Architecture Differences

The two processors come from fundamentally different design philosophies. The Intel Xeon 636 is built on Intel's 5 nm process and uses the Granite Rapids architecture, part of the Xeon 600 generation (Granite Rapids-WS). The AMD Ryzen 5 PRO 9645 uses TSMC's 4 nm process with the Granite Ridge codename, belonging to the Ryzen 7 generation built on Zen 5 (Granite Ridge). The smaller process node from TSMC gives AMD a manufacturing density advantage.

Core counts differ substantially. The Intel Xeon 636 offers 12 cores and 24 threads, while the AMD Ryzen 5 PRO 9645 provides 6 cores and 12 threads. This 2x core and thread advantage for Intel explains much of its multi-threaded benchmark dominance. Clock speeds, however, favor AMD. The Ryzen 5 PRO 9645 has a 3.90 GHz base clock and a 5.40 GHz boost clock, compared to the Xeon 636's 3.50 GHz base and 4.70 GHz boost.

Cache hierarchies also diverge. The Intel part allocates 112 KB of L1 cache per core, 2 MB of L2 per core, and 48 MB of shared L3 cache. The AMD chip uses 80 KB of L1 per core, 1 MB of L2 per core, and 32 MB of shared L3. Intel's larger cache pool, combined with its higher core count, reinforces its strength in data-heavy workloads.

Memory subsystems show major differences. The Intel Xeon 636 supports quad-channel DDR5 with a memory bandwidth of 204.8 GB/s. The AMD Ryzen 5 PRO 9645 uses dual-channel DDR5 with 89.6 GB/s of bandwidth. That is a roughly 2.3x bandwidth advantage for Intel, which matters for server and workstation tasks that stream large datasets. Both support ECC memory, and both use DDR5. PCIe connectivity also differs: Intel provides Gen 5 with 80 CPU lanes, while AMD provides Gen 5 with 24 CPU lanes.

The physical packages reflect their different targets. The Intel Xeon 636 uses Intel Socket 4710 and has a die size of 598 mm². The AMD Ryzen 5 PRO 9645 uses AMD Socket AM5 and has a die size of 70.6 mm², with 8,315 million transistors. The Intel part has no integrated graphics, while the AMD chip includes Radeon Graphics. Power envelopes diverge sharply: the Intel Xeon 636 has a TDP of 170, while the AMD Ryzen 5 PRO 9645 has a TDP of 65. The Intel processor also has an unlocked multiplier, whereas the AMD part is locked. Intel's launch MSRP is $639, and its release date is 2026-02-01; AMD's release date is 2025-09-15.

FAQ

Q: Which processor is faster in multi-threaded workloads?

A: The Intel Xeon 636. It leads by 41.3% in PassMark multithread (44421 versus 31434) and by 87.4% in PassMark physics (3645 versus 1945). Its 12 cores and 24 threads provide a substantial advantage over the AMD's 6 cores and 12 threads.

Q: Does the AMD Ryzen 5 PRO 9645 win any benchmarks?

A: Yes, it wins both recorded single-thread tests. In PassMark single thread, it scores 4636 against Intel's 3937, a 15.1% advantage.

Q: How do these chips compare to other CPUs in the database?

A: Both sit at the 92nd percentile among all CPUs. The Intel Xeon 636 has an average benchmark score of 61360, placing it near the Intel Core i9-13900T (61723, within 0.6%) and Intel Core i9-13900K (61766, within 0.7%). The AMD Ryzen 5 PRO 9645 averages 58916, which is 0.2% ahead of the AMD Ryzen AI 9 HX 470 and 0.7% ahead of the Intel Xeon w5-2545.

Q: What are the memory bandwidth differences?

A: The Intel Xeon 636 supports quad-channel DDR5 with 204.8 GB/s of bandwidth. The AMD Ryzen 5 PRO 9645 supports dual-channel DDR5 with 89.6 GB/s. Both support ECC memory.

Q: Which processor has higher clock speeds?

A: The AMD Ryzen 5 PRO 9645. It has a 3.90 GHz base clock and a 5.40 GHz boost clock. The Intel Xeon 636 has a 3.50 GHz base clock and a 4.70 GHz boost clock.

Q: Do these processors include integrated graphics?

A: No for Intel, yes for AMD. The Intel Xeon 636 lists integrated graphics as N/A, while the AMD Ryzen 5 PRO 9645 includes Radeon Graphics.

The Verdict

The data points to a clear split based on workload type. For multi-threaded, data-intensive, and server-oriented tasks, the Intel Xeon 636 is the stronger choice. Its wins across physics, floating point math, encryption, compression, integer math, and multithread tests are decisive, with margins ranging from 41.3% to 87.4%. The 12-core, 24-thread configuration, larger caches, and quad-channel memory bandwidth at 204.8 GB/s make it well suited for workloads that scale across cores and demand high memory throughput.

For single-threaded responsiveness, the AMD Ryzen 5 PRO 9645 is the better option. Its 15.1% lead in PassMark single thread, combined with a 5.40 GHz boost clock, gives it an edge in lightly threaded applications. The lower TDP of 65 also makes it a far more efficient part in terms of power draw, and its smaller die size and integrated Radeon Graphics add flexibility for compact or power-conscious systems.

The average benchmark scores reinforce this assessment. The Intel Xeon 636 posts 61360 overall, while the AMD Ryzen 5 PRO 9645 posts 58916. Both are at the 92nd percentile, so neither is a weak performer. The choice depends on whether the priority is raw multi-threaded throughput or single-thread speed with lower power consumption.

Specification Differences

| Specification | Intel Xeon 636 | AMD Ryzen 5 PRO 9645 |

|---|---|---|

| Cores | 12 | 6 |

| Threads | 24 | 12 |

| Base clock | 3.50 GHz | 3.90 GHz |

| Boost clock | 4.70 GHz | 5.40 GHz |

| TDP | 170 | 65 |

| Socket | Intel Socket 4710 | AMD Socket AM5 |

| Codename | Granite Rapids | Granite Ridge |

| Generation | Xeon 600 (Granite Rapids-WS) | Ryzen 7 (Zen 5, Granite Ridge) |

| Process node | 5 nm | 4 nm |

| Foundry | Intel | TSMC |

| Die size | 598 mm² | 70.6 mm² |

| Transistors | N/A | 8,315 million |

| L1 cache | 112 KB (per core) | 80 KB (per core) |

| L2 cache | 2 MB (per core) | 1 MB (per core) |

| L3 cache | 48 MB (shared) | 32 MB (shared) |

| Memory bus | Quad-channel | Dual-channel |

| Memory bandwidth | 204.8 GB/s | 89.6 GB/s |

| PCIe | Gen 5, 80 lanes (CPU only) | Gen 5, 24 lanes (CPU only) |

| Integrated graphics | N/A | Radeon Graphics |

| Multiplier unlocked | Yes | No |

| Release date | 2026-02-01 | 2025-09-15 |

| Launch MSRP | $639 | N/A |