AMD EPYC 9535 vs Intel Xeon 6980P Comparison

The Verdict

The benchmark data draws a clear line between these two server processors. The AMD EPYC 9535 wins 8 of the 11 recorded head-to-head tests, while the Intel Xeon 6980P takes 3. The AMD part leads by massive margins in several workloads, including a 121.3% advantage in single-thread performance and a 54.1% lead in multithreaded throughput. The Intel Xeon 6980P counters with an 18.2% win in extended instructions and an 8.9% edge in floating-point math, but those victories do not offset the breadth of AMD's dominance.

For workloads that depend on single-thread responsiveness, database operations, or integer-heavy processing, the AMD EPYC 9535 is the clear choice. For extended instruction workloads and floating-point math, the Intel Xeon 6980P holds an advantage. The overall average benchmark score reinforces this: the AMD EPYC 9535 records 379408 versus 251516 for the Intel part, a gap that places the AMD chip at the 100th percentile of all CPUs while the Intel chip sits at the 99th percentile.

The launch MSRP of the AMD EPYC 9535 is $8992, while the Intel Xeon 6980P has a launch MSRP of $12460. The AMD chip also carries a lower TDP of 300 watts compared to 500 watts for the Intel part.

Architecture Differences

The two processors come from fundamentally different design philosophies. The AMD EPYC 9535 belongs to the EPYC 9005 series and uses the Zen 5 architecture under the Turin codename. It is built on a 4 nm process at TSMC, with 66,520 million transistors spread across 8 chiplets, each measuring 70.6 mm². The Intel Xeon 6980P uses the Granite Rapids architecture, built on a 5 nm process at Intel, with a die size of 3x 598 mm².

Core counts differ substantially. The AMD chip provides 64 cores and 128 threads, while the Intel chip doubles that to 128 cores and 256 threads. Despite having half the cores, the AMD EPYC 9535 wins the multithreaded PassMark test by 54.1%, which points to a significant per-core efficiency advantage. Clock speeds tell part of the story: the AMD part has a base clock of 2.40 GHz and a boost clock of 4.30 GHz, while the Intel part operates at 2.00 GHz base and 3.90 GHz boost.

Cache hierarchies also diverge. The AMD EPYC 9535 has 80 KB of L1 cache per core, 1 MB of L2 per core, and 256 MB of shared L3 cache. The Intel Xeon 6980P has 112 KB of L1 per core, 2 MB of L2 per core, and a much larger 504 MB of shared L3. The Intel part's larger cache pool does not translate into benchmark superiority, as the AMD chip wins most tests despite the cache deficit.

Memory support is similar in structure: both use DDR5 with a twelve-channel memory bus. The Intel part has a higher peak memory bandwidth at 614.4 GB/s versus 576.0 GB/s for AMD. Both support ECC memory. PCIe connectivity differs: the AMD EPYC 9535 offers Gen 5 with 128 lanes, while the Intel Xeon 6980P offers Gen 5 with 96 lanes.

Sockets are incompatible: the AMD chip uses AMD Socket SP5, while the Intel chip uses Intel Socket 7529. Both are active production parts. The AMD EPYC 9535 was released on 2024-10-09, and the Intel Xeon 6980P was released on 2024-09-23.

FAQ

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

A: The AMD EPYC 9535 scores 3720 in the PassMark single-thread test, which is 121.3% higher than the Intel Xeon 6980P's score of 1681. This is the largest performance gap recorded between the two chips.

Q: Does the Intel Xeon 6980P win any benchmark tests?

A: Yes, the Intel Xeon 6980P wins 3 tests: data compression by 2.4%, extended instructions by 18.2%, and floating-point math by 8.9%.

Q: How do the two processors compare in multithreaded performance?

A: The AMD EPYC 9535 scores 114528 in the PassMark multithread test, beating the Intel Xeon 6980P's 74324 by 54.1%. This is notable because the Intel chip has twice as many cores and threads.

Q: What is the average benchmark score for each processor?

A: The AMD EPYC 9535 has an average benchmark score of 379408, which is 3.9% higher than the Intel Xeon 6960P's score of 365194 and 4.1% higher than the AMD EPYC 9754's 364371. The Intel Xeon 6980P has an average score of 251516, which is 3% higher than the AMD EPYC 9634's 244274.

Q: Which processor has a higher core count?

A: The Intel Xeon 6980P has 128 cores and 256 threads, while the AMD EPYC 9535 has 64 cores and 128 threads. The Intel part doubles the core and thread counts.

Q: How does the AMD EPYC 9535 compare to its nearest rivals?

A: The AMD EPYC 9535 has an average score of 379408. It is 1.6% higher than the AMD EPYC 9655's score of 373479 and 3.9% higher than the Intel Xeon 6960P's 365194. The AMD EPYC 9655P scores higher at 397773, which is 4.6% above the EPYC 9535.

Specification Differences

The two processors differ across nearly every major specification category. The AMD EPYC 9535 uses the Zen 5 architecture on a 4 nm process, while the Intel Xeon 6980P uses Granite Rapids on a 5 nm process. The foundries differ: TSMC for AMD, Intel for the Xeon. The AMD chip has 66,520 million transistors across 8x 70.6 mm² dies, while the Intel chip has no recorded transistor count and uses 3x 598 mm² dies.

Core and thread counts differ by a factor of two: 64 cores and 128 threads for AMD, 128 cores and 256 threads for Intel. Base clocks are 2.40 GHz versus 2.00 GHz, and boost clocks are 4.30 GHz versus 3.90 GHz. TDP stands at 300 watts for AMD and 500 watts for Intel. Sockets are completely different: AMD Socket SP5 versus Intel Socket 7529.

Cache configurations differ at every level. L1 cache is 80 KB per core for AMD and 112 KB per core for Intel. L2 cache is 1 MB per core for AMD and 2 MB per core for Intel. Shared L3 cache is 256 MB for AMD and 504 MB for Intel. Memory bandwidth favors Intel at 614.4 GB/s versus 576.0 GB/s, though both use DDR5 over a twelve-channel bus.

PCIe lane counts favor AMD: 128 lanes versus 96 lanes, both Gen 5. The AMD part launched on 2024-10-09 with a launch MSRP of $8992, while the Intel part launched on 2024-09-23 with a launch MSRP of $12460. Both have no integrated graphics and both support ECC memory. Neither processor has an unlocked multiplier.

Head-to-Head Benchmarks

The PassMark test suite reveals a lopsided contest. The AMD EPYC 9535 wins the single-thread test by 121.3%, scoring 3720 against 1681. This margin is enormous and suggests a substantial per-core performance difference. The multithread test shows a 54.1% lead for AMD, with scores of 114528 against 74324. Integer math also goes to AMD by 14.6%, with 730281 against 637476.

Prime number finding is a decisive AMD victory. The EPYC 9535 scores 874, which is 57.5% higher than the Intel chip's 555. Physics simulation favors AMD by 14.4%, with 3834 against 3350. Random string sorting goes to AMD by a slim 2.8%, with 247506 against 240792. Data encryption also favors AMD by 1.7%, with 127372 against 125246.

The Intel Xeon 6980P claims three wins. Extended instructions show an 18.2% lead for Intel, scoring 214794 against 175784. Floating-point math goes to Intel by 8.9%, with 501720 against 457047. Data compression is the closest Intel victory at 2.4%, with 2364519 against 2308822.

The overall benchmark averages place the AMD EPYC 9535 well ahead. Its average score of 379408 compares to 251516 for the Intel Xeon 6980P. The AMD part sits at the 100th percentile of all CPUs, while the Intel part sits at the 99th percentile. The AMD EPYC 9535 also sits 1.6% above the AMD EPYC 9655 and 3.9% above the Intel Xeon 6960P in average score, while the Intel Xeon 6980P sits 3% above the AMD EPYC 9634 and 5.6% above the Intel Xeon 6747P.

Where Each One Wins

The AMD EPYC 9535 dominates in scenarios that demand single-thread responsiveness. The 121.3% lead in single-thread performance makes it the better choice for latency-sensitive applications, database transactions, and workloads that cannot fully parallelize. The 54.1% multithread advantage is equally significant, showing that the AMD chip delivers higher aggregate throughput despite having half the cores of the Intel part. Integer math, prime number finding, physics simulation, random string sorting, and data encryption all favor AMD, covering a broad swath of general-purpose server workloads.

The Intel Xeon 6980P wins in three specific areas. Its 18.2% advantage in extended instructions suggests a strength in vectorized or specialized instruction workloads. The 8.9% lead in floating-point math points to scientific computing or simulation tasks that rely heavily on floating-point arithmetic. The 2.4% win in data compression is narrow but real, indicating a slight edge in compression-heavy pipelines.

For buyers choosing between these two, the data favors the AMD EPYC 9535 for most workloads. The Intel Xeon 6980P offers more cores, more cache, and higher memory bandwidth, yet it trails in most measured tests. The AMD chip's higher clock speeds, lower TDP, and better per-core efficiency translate directly into benchmark wins. The Intel part remains competitive only in extended instructions and floating-point math, which are meaningful niches but not enough to offset the AMD advantage elsewhere. The AMD EPYC 9535 also achieves its results with 300 watts of TDP against 500 watts for the Intel part, and it carries a lower launch MSRP of $8992 compared to $12460.