AMD EPYC 9655 vs Intel Xeon 6780E Comparison

Head-to-Head Benchmarks

The head-to-head data is unambiguous: the AMD EPYC 9655 wins all 16 recorded benchmarks against the Intel Xeon 6780E. The most dominant margins appear in CPU-intensive workloads. In Cinebench R23 multi-core, the EPYC 9655 scores 132,672 versus 73,723 for the Xeon, an 80% advantage. The same 80% delta appears in Cinebench R15 multi-core (13,373 vs. 7,431) and R20 multi-core (55,722 vs. 30,963). These are not marginal differences; they represent a consistent, near-doubling of rendering throughput in every multi-threaded Cinebench iteration.

Single-core results tell a similar story. The EPYC 9655 leads by 79.9% in Cinebench R15 single-core (1,887 vs. 1,049) and by 80% in R20 single-core (7,866 vs. 4,371). PassMark single-thread shows a 100.1% lead (3,847 vs. 1,923), meaning the AMD part effectively doubles the per-thread performance of the Intel chip. This is a critical finding: the Xeon 6780E cannot compensate for its core count advantage through higher clock speeds or better single-thread efficiency.

The largest percentage deltas appear in PassMark physics and prime-number finding. The EPYC 9655 records 25,947 in PassMark physics versus 10,951 for the Xeon, a 136.9% lead. In find-prime-numbers, the AMD part scores 1,598 against 708, a 125.7% delta. These tests are sensitive to floating-point throughput and branch handling, and the data indicates the Zen 5 architecture is far stronger in these specific operations.

Smaller but still decisive leads exist in data compression and encryption. The EPYC 9655 scores 3,271,896 in PassMark data compression versus 2,557,582, a 27.9% advantage. In data encryption, the lead narrows to 9.1% (210,555 vs. 193,004). Extended instructions show a 78.3% gap (203,285 vs. 114,008), while floating-point math favors the AMD part by 52.8% (662,958 vs. 433,862). Integer math is also lopsided: 1,139,161 vs. 641,817, a 77.5% delta. Random string sorting completes the sweep with a 34.5% lead (439,682 vs. 326,954).

The average benchmark score reinforces the pattern. The EPYC 9655 averages 373,479 across all recorded tests, while the Xeon 6780E averages 280,438. When placed against the nearest rivals, the EPYC 9655 sits at the 100th percentile of all CPUs, with its closest competitor being the AMD EPYC 9535 at -1.6% and the Intel Xeon 6960P at +2.3% behind. The Xeon 6780E, by contrast, sits at the 99th percentile, with its nearest rival being the AMD Ryzen Threadripper 9970X at +0.2% and the AMD EPYC 9565 at -1.8%.

Where Each One Wins

The AMD EPYC 9655 wins every workload category in the database. There is no recorded test where the Intel Xeon 6780E takes the lead. However, the magnitude of the win varies significantly by workload type, which matters for deployment decisions.

For rendering and multi-threaded compute, the EPYC 9655 is the clear choice. Cinebench multi-core results consistently show an 80% advantage, which translates directly to shorter render times for 3D workloads or simulation tasks that scale across cores. The PassMark multithread score of 156,110 versus 86,734 (80% delta) confirms that the AMD part handles parallel workloads substantially better despite having fewer cores.

For single-threaded or latency-sensitive tasks, the EPYC 9655 is equally dominant. The 100.1% lead in PassMark single-thread means that any application that cannot fully utilize many cores will still run significantly faster on the AMD platform. This is relevant for database servers, web front-ends, or any workload with serial dependencies.

For data processing and compression, the EPYC 9655 maintains a comfortable but smaller edge. The 27.9% lead in data compression and 9.1% lead in encryption suggest that memory-bandwidth-bound operations narrow the gap, but the AMD part still wins decisively. The Xeon 6780E's larger core count (144 vs. 96) does not translate into a win in these tests, likely due to lower per-core performance and lower memory bandwidth.

The Xeon 6780E would only be preferable in scenarios where its 144 cores and lower TDP (330 vs. 400) align with specific power or density constraints. The data shows no benchmark where it outperforms the EPYC 9655, but its higher core count and lower thermal envelope could make it attractive for scale-out deployments where raw per-core performance is secondary to core density. That said, the benchmark results indicate that even in heavily threaded workloads, the EPYC 9655's superior architecture overcomes the core deficit.

Architecture Differences

The two processors represent fundamentally different design philosophies. The AMD EPYC 9655 uses the Zen 5 architecture, codenamed Turin, built on a 4 nm process by TSMC. It packs 96 cores and 192 threads, with a base clock of 2.60 GHz and a boost clock of 4.50 GHz. The Intel Xeon 6780E uses the Sierra Forest architecture, also codenamed Sierra Forest, built on a 5 nm process by Intel. It contains 144 cores but only 144 threads, indicating no hyperthreading, with a base clock of 2.20 GHz and a boost clock of 3.00 GHz.

The transistor counts differ dramatically. The EPYC 9655 contains 99,780 million transistors spread across 12 dies, each 70.6 mm² in size. The Xeon 6780E has a single 578 mm² die, with no transistor count listed in the database. This die-level difference explains the EPYC's higher TDP of 400 watts versus 330 watts for the Xeon, but also contributes to the AMD part's superior clock speeds and per-core efficiency.

Cache hierarchies are also distinct. The EPYC 9655 offers 80 KB of L1 cache per core, 1 MB of L2 per core, and a massive 384 MB of shared L3 cache. The Xeon 6780E provides 96 KB of L1 per core and 4 MB of L2 per module, but only 108 MB of shared L3 cache. The EPYC's 384 MB L3 cache is more than triple the Xeon's, which directly boosts performance in cache-sensitive workloads like the PassMark extended instructions test (78.3% lead).

Memory support shows further divergence. Both support DDR5 and ECC memory, but the EPYC 9655 runs twelve-channel memory with a bandwidth of 576.0 GB/s. The Xeon 6780E runs eight-channel memory with a bandwidth of 409.6 GB/s. This 166.4 GB/s difference in theoretical memory bandwidth likely contributes to the EPYC's wins in data compression and random string sorting, where memory throughput is a limiting factor.

PCIe lane counts also differ. The EPYC 9655 provides Gen 5 with 128 lanes (CPU only), while the Xeon 6780E provides Gen 5 with 88 lanes (CPU only). For systems requiring many NVMe drives or high-speed accelerators, the EPYC's additional 40 lanes offer more expansion headroom. Both processors lack integrated graphics and have locked multipliers.

FAQ

Q: Which processor has more cores?

A: The Intel Xeon 6780E has 144 cores, which is 48 more than the AMD EPYC 9655's 96 cores. However, the EPYC 9655 supports 192 threads via simultaneous multithreading, while the Xeon 6780E has only 144 threads (no hyperthreading).

Q: Which processor has higher clock speeds?

A: The AMD EPYC 9655 has a base clock of 2.60 GHz and a boost clock of 4.50 GHz. The Intel Xeon 6780E has a base clock of 2.20 GHz and a boost clock of 3.00 GHz. The EPYC's boost clock is 1.50 GHz higher.

Q: How much larger is the L3 cache on the AMD part?

A: The AMD EPYC 9655 has 384 MB of shared L3 cache, while the Intel Xeon 6780E has 108 MB of shared L3 cache. That is a 276 MB difference, or roughly 3.6 times more L3 on the AMD side.

Q: What is the memory bandwidth difference?

A: The AMD EPYC 9655 supports twelve-channel DDR5 memory with a theoretical bandwidth of 576.0 GB/s. The Intel Xeon 6780E supports eight-channel DDR5 with 409.6 GB/s. The AMD part offers 166.4 GB/s more bandwidth.

Q: Which processor has a higher TDP?

A: The AMD EPYC 9655 has a TDP of 400 watts, while the Intel Xeon 6780E has a TDP of 330 watts. The AMD part consumes 70 watts more, which reflects its higher clock speeds and larger L3 cache.

Q: How do their release dates compare?

A: The Intel Xeon 6780E was released on 2024-06-02, while the AMD EPYC 9655 was released on 2024-10-09. The AMD part launched approximately four months later.

Specification Differences

| Specification | AMD EPYC 9655 | Intel Xeon 6780E |

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

| Cores | 96 | 144 |

| Threads | 192 | 144 |

| Base Clock | 2.60 GHz | 2.20 GHz |

| Boost Clock | 4.50 GHz | 3.00 GHz |

| TDP | 400 W | 330 W |

| Socket | AMD Socket SP5 | Intel Socket 4710 |

| Architecture | Zen 5 | Sierra Forest |

| Process Node | 4 nm (TSMC) | 5 nm (Intel) |

| Transistors | 99,780 million | Not listed |

| Die Size | 12x 70.6 mm² | 578 mm² |

| L1 Cache (per core) | 80 KB | 96 KB |

| L2 Cache (per core/module) | 1 MB (per core) | 4 MB (per module) |

| L3 Cache (shared) | 384 MB | 108 MB |

| Memory Bus | Twelve-channel | Eight-channel |

| Memory Bandwidth | 576.0 GB/s | 409.6 GB/s |

| PCIe Lanes (CPU only) | Gen 5, 128 | Gen 5, 88 |

| Launch MSRP | $11852 | $11350 |

| Part Number | 100-000000674 | SRPG3 |

The Verdict

The data points to a decisive recommendation for the AMD EPYC 9655 in nearly every server and workstation scenario. It wins all 16 recorded benchmarks, with leads ranging from 9.1% in data encryption to 136.9% in physics. The EPYC 9655 offers more than double the single-thread performance of the Xeon 6780E and an 80% advantage in multi-threaded Cinebench workloads, despite having 48 fewer cores.

The Xeon 6780E's only advantages are its lower TDP (330 vs. 400 watts), its higher core count (144 vs. 96), and a lower launch MSRP ($11,350 vs. $11,852). For deployments where core count per socket is the primary metric and power efficiency is paramount, the Xeon 6780E remains a viable option. However, the benchmark data shows that the EPYC 9655's superior clocks, larger L3 cache, and higher memory bandwidth overcome the core deficit in every measured workload.

For organizations running Cinebench-class rendering, PassMark physics, floating-point math, or integer-heavy applications, the EPYC 9655 is the clear choice. Its 100th percentile ranking versus the Xeon's 99th percentile further confirms this. The launch MSRP difference of $502 is minimal relative to the performance gap. The verdict is straightforward: the AMD EPYC 9655 is the faster processor by a wide margin across all recorded metrics, and the Intel Xeon 6780E should only be selected when its specific power and core-density profile outweighs the substantial performance disadvantage.