AMD Ryzen 9 PRO 9945 vs Intel Core Ultra 9 290K Plus Comparison

Where Each One Wins

The recorded data splits this comparison into two very different profiles. The AMD Ryzen 9 PRO 9945 wins exactly one benchmark in the head-to-head set: PassMark integer math, scoring 171,175 versus 166,194 for the Intel Core Ultra 9 290K Plus, a 3% advantage. That is the only category where AMD takes the lead. Every other measured workload favors the Intel part, often by substantial margins.

The Intel Core Ultra 9 290K Plus dominates the throughput-oriented tests. Its largest victory is in floating-point math, where it scores 214,760 against 107,340, a 50% delta. Data encryption shows a 42.1% gap, with Intel at 52,563 versus AMD's 30,450. Prime number finding favors Intel by 32%, and data compression by 17%. The multithread PassMark score also goes to Intel, 60,860 versus 48,664, a 20% difference. Even the single-thread results lean Intel, though narrowly: 4,823 versus 4,619, a 4.2% edge.

For integer-heavy general computation, the AMD part holds a small but genuine advantage. For everything else, from encryption to floating-point workloads, the Intel part is the clear performer. The win tally reflects this: Intel claims 10 head-to-head victories, AMD claims 1. The use-case split is straightforward: if the workload is dominated by integer arithmetic, AMD's 12-core design keeps pace; if the workload involves heavy floating-point math, encryption, compression, or broad multithreading, the Intel part pulls ahead decisively.

Architecture Differences

The two processors come from fundamentally different design philosophies. The AMD Ryzen 9 PRO 9945 uses the Granite Ridge architecture, built on a 4 nm TSMC process, with 12 cores and 24 threads. The Intel Core Ultra 9 290K Plus uses Arrow Lake Refresh, on a 3 nm TSMC process, with 24 cores and 24 threads. The core count difference is significant: Intel doubles the physical cores, but both parts present the same thread count because Intel's design does not use simultaneous multithreading in this generation.

Cache organization differs sharply. AMD allocates 80 KB of L1 per core, 1 MB of L2 per core, and a 64 MB L3 pool. Intel allocates 192 KB of L1 per core, 3 MB of L2 per core, and a 36 MB shared L3. Intel's per-core cache is larger, but its total L3 is roughly half of AMD's. The AMD part has a two-chiplet design with a die size of 2x 70.6 mm², while Intel uses a monolithic 243 mm² die. Transistor counts are close: AMD lists 16,630 million, Intel lists 17,800 million.

Memory support is DDR5 on both, with dual-channel buses. However, Intel's memory bandwidth is rated at 115.2 GB/s versus AMD's 89.6 GB/s. Both support ECC memory. PCIe generation matches at Gen 5, but AMD provides 24 CPU lanes versus Intel's 20. Integrated graphics differ: AMD has Radeon Graphics, Intel has Arc Xe-LPG Graphics 64EU.

Power characteristics diverge substantially. The AMD part carries a 65 W TDP, while the Intel part is rated at 125 W. Clock speeds also favor Intel: base 3.70 GHz versus 3.40 GHz, boost 5.80 GHz versus 5.40 GHz. The AMD multiplier is locked; the Intel multiplier is unlocked. Socket compatibility is entirely separate: AMD Socket AM5 versus Intel Socket 1851. The AMD part targets the server/workstation segment and was released in September 2025; the Intel part targets desktop, with no recorded release date.

FAQ

Q: Which processor has a higher boost clock?

A: The Intel Core Ultra 9 290K Plus boosts to 5.80 GHz, while the AMD Ryzen 9 PRO 9945 boosts to 5.40 GHz.

Q: How do the core counts compare?

A: The Intel part has 24 cores and 24 threads, while the AMD part has 12 cores and 24 threads. Both present 24 threads to software.

Q: Which processor has more L3 cache?

A: The AMD Ryzen 9 PRO 9945 has 64 MB of L3 cache, exactly double the Intel Core Ultra 9 290K Plus's 36 MB shared L3.

Q: What is the memory bandwidth difference?

A: Intel rates its dual-channel DDR5 memory bus at 115.2 GB/s, compared to AMD's 89.6 GB/s, a 28.6% higher theoretical bandwidth.

Q: Does either processor support ECC memory?

A: Yes, both the AMD Ryzen 9 PRO 9945 and the Intel Core Ultra 9 290K Plus support ECC memory.

Q: Which processor has a lower TDP?

A: The AMD Ryzen 9 PRO 9945 has a 65 W TDP, while the Intel Core Ultra 9 290K Plus has a 125 W TDP.

Specification Differences

| Specification | AMD Ryzen 9 PRO 9945 | Intel Core Ultra 9 290K Plus |

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

| Cores | 12 | 24 |

| Threads | 24 | 24 |

| Base clock | 3.40 GHz | 3.70 GHz |

| Boost clock | 5.40 GHz | 5.80 GHz |

| TDP | 65 W | 125 W |

| Socket | AMD Socket AM5 | Intel Socket 1851 |

| Process node | 4 nm | 3 nm |

| Die size | 2x 70.6 mm² | 243 mm² |

| Transistors | 16,630 million | 17,800 million |

| L1 cache (per core) | 80 KB | 192 KB |

| L2 cache (per core) | 1 MB | 3 MB |

| L3 cache | 64 MB | 36 MB (shared) |

| Memory bandwidth | 89.6 GB/s | 115.2 GB/s |

| PCIe lanes (CPU) | Gen 5, 24 Lanes | Gen 5, 20 Lanes |

| Integrated graphics | Radeon Graphics | Arc Xe-LPG Graphics 64EU |

| Multiplier unlocked | No | Yes |

| Market segment | Server/Workstation | Desktop |

Head-to-Head Benchmarks

The benchmark matrix shows a clear pattern. Intel takes 10 of 11 tests, but the magnitudes vary widely. The single most lopsided result is PassMark floating-point math. Intel scores 214,760, AMD scores 107,340. That is exactly double, a 50% delta. For workloads that stress FPU pipelines, this is not a close contest.

Data encryption shows the second-largest gap. Intel's 52,563 beats AMD's 30,450 by 42.1%. This suggests the Intel part has stronger cryptographic acceleration paths or better throughput per clock for these operations. Prime number finding follows at 32% (503 versus 342), then random string sorting at 21.7% (79,744 versus 62,458), and multithread at 20% (60,860 versus 48,664).

The compression test gives Intel a 17% edge (698,346 versus 579,972). Extended instructions go to Intel by 15.2% (52,338 versus 44,374). Physics simulation favors Intel by 12.5% (3,315 versus 2,902). Single-thread performance is the closest Intel win: 4,823 versus 4,619, only 4.2%.

The sole AMD win is integer math. AMD scores 171,175 against Intel's 166,194, a 3% margin. This is a small but consistent edge in a fundamental workload. The average benchmark scores from the database put AMD at 96,083 and Intel at 84,003, but this aggregate includes different test sets for each part. In the direct head-to-head comparisons, Intel's advantage is dominant.

Percentile rankings against all CPUs are identical: both sit at the 96th percentile. The nearest rivals for AMD include the AMD EPYC 4565P (0.3% ahead), AMD EPYC 9175F (0.5% ahead), and AMD EPYC 4564P (0.9% ahead), with the Ryzen 9 9955HX3D trailing by 1.4%. For Intel, the closest competitor is the Intel Core Ultra 9 285K at 0.2%, followed by AMD EPYC 4584PX at 1.1% and AMD EPYC 9135 at 1.2%, with the AMD EPYC 7F72 trailing by 1.3%. Both parts are tightly clustered among their peers.

The data indicates that the Intel Core Ultra 9 290K Plus is the stronger all-round performer in this head-to-head, with particular strengths in floating-point and encryption workloads. The AMD Ryzen 9 PRO 9945 retains a niche advantage in integer math and offers a substantially lower TDP, which may matter for dense server deployments where power envelope is a constraint.