EPYC 9654 vs Xeon E5-2699 v3
Aggregate performance score
EPYC 9654 outperforms Xeon E5-2699 v3 by a whopping 490% based on our aggregate benchmark results.
Primary details
Comparing Xeon E5-2699 v3 and EPYC 9654 processor market type (desktop or notebook), architecture, sales start time and price.
| Place in the ranking | 592 | 6 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 1.29 |
| Market segment | Server | Server |
| Series | no data | AMD EPYC |
| Power efficiency | 8.37 | 19.91 |
| Architecture codename | Haswell-EP (2014−2015) | Genoa (2022−2023) |
| Release date | 8 September 2014 (10 years ago) | 10 November 2022 (2 years ago) |
| Launch price (MSRP) | no data | $11,805 |
Cost-effectiveness evaluation
Performance per price, higher is better.
Detailed specifications
Xeon E5-2699 v3 and EPYC 9654 basic parameters such as number of cores, number of threads, base frequency and turbo boost clock, lithography, cache size and multiplier lock state. These parameters indirectly say of CPU speed, though for more precise assessment you have to consider their test results.
| Physical cores | 18 (Octadeca-Core) | 96 |
| Threads | 36 | 192 |
| Base clock speed | 2.3 GHz | 2.4 GHz |
| Boost clock speed | 3.6 GHz | 3.7 GHz |
| Bus rate | 9.6 GT/s | no data |
| Multiplier | no data | 24 |
| L1 cache | 64K (per core) | 64K (per core) |
| L2 cache | 256K (per core) | 1 MB (per core) |
| L3 cache | 45 MB (shared) | 384 MB (shared) |
| Chip lithography | 22 nm | 5 nm, 6 nm |
| Die size | 356 mm2 | 12x 72 mm2 |
| Maximum case temperature (TCase) | 77 °C | no data |
| Number of transistors | 2,600 million | 78,840 million |
| 64 bit support | + | + |
| Windows 11 compatibility | - | no data |
Compatibility
Information on Xeon E5-2699 v3 and EPYC 9654 compatibility with other computer components: motherboard (look for socket type), power supply unit (look for power consumption) etc. Useful when planning a future computer configuration or upgrading an existing one. Note that power consumption of some processors can well exceed their nominal TDP, even without overclocking. Some can even double their declared thermals given that the motherboard allows to tune the CPU power parameters.
| Number of CPUs in a configuration | 2 | 2 |
| Socket | FCLGA2011 | SP5 |
| Power consumption (TDP) | 145 Watt | 360 Watt |
Technologies and extensions
Technological solutions and additional instructions supported by Xeon E5-2699 v3 and EPYC 9654. You'll probably need this information if you require some particular technology.
| Instruction set extensions | Intel® AVX2 | no data |
| AES-NI | + | + |
| AVX | + | + |
| vPro | + | no data |
| Enhanced SpeedStep (EIST) | + | no data |
| Turbo Boost Technology | 2.0 | no data |
| Hyper-Threading Technology | + | no data |
| Idle States | + | no data |
| Thermal Monitoring | + | - |
| Flex Memory Access | - | no data |
| Demand Based Switching | + | no data |
| PAE | 46 Bit | no data |
| Precision Boost 2 | no data | + |
Security technologies
Xeon E5-2699 v3 and EPYC 9654 technologies aimed at improving security, for example, by protecting against hacks.
| TXT | + | no data |
| EDB | + | no data |
| Secure Key | + | no data |
| OS Guard | + | no data |
Virtualization technologies
Virtual machine speed-up technologies supported by Xeon E5-2699 v3 and EPYC 9654 are enumerated here.
| AMD-V | - | + |
| VT-d | + | no data |
| VT-x | + | no data |
| EPT | + | no data |
Memory specs
Types, maximum amount and channel quantity of RAM supported by Xeon E5-2699 v3 and EPYC 9654. Depending on the motherboard, higher memory frequencies may be supported.
| Supported memory types | DDR4-1600, DDR4-1866, DDR4-2133 | DDR5-4800 |
| Maximum memory size | 768 GB | 6 TiB |
| Max memory channels | 4 | no data |
| Maximum memory bandwidth | 68 GB/s | 460.8 GB/s |
| ECC memory support | + | - |
Peripherals
Specifications and connection of peripherals supported by Xeon E5-2699 v3 and EPYC 9654.
| PCIe version | 3.0 | 5.0 |
| PCI Express lanes | 40 | 128 |
Synthetic benchmark performance
Various benchmark results of the processors in comparison. Overall score is measured in points in 0-100 range, higher is better.
Combined synthetic benchmark score
This is our combined benchmark performance rating. We are regularly improving our combining algorithms, but if you find some perceived inconsistencies, feel free to speak up in comments section, we usually fix problems quickly.
Passmark
Passmark CPU Mark is a widespread benchmark, consisting of 8 different types of workload, including integer and floating point math, extended instructions, compression, encryption and physics calculation. There is also one separate single-threaded scenario measuring single-core performance.
GeekBench 5 Single-Core
GeekBench 5 Single-Core is a cross-platform application developed in the form of CPU tests that independently recreate certain real-world tasks with which to accurately measure performance. This version uses only a single CPU core.
GeekBench 5 Multi-Core
GeekBench 5 Multi-Core is a cross-platform application developed in the form of CPU tests that independently recreate certain real-world tasks with which to accurately measure performance. This version uses all available CPU cores.
Pros & cons summary
| Performance score | 12.83 | 75.73 |
| Recency | 8 September 2014 | 10 November 2022 |
| Physical cores | 18 | 96 |
| Threads | 36 | 192 |
| Chip lithography | 22 nm | 5 nm |
| Power consumption (TDP) | 145 Watt | 360 Watt |
Xeon E5-2699 v3 has 148.3% lower power consumption.
EPYC 9654, on the other hand, has a 490.3% higher aggregate performance score, an age advantage of 8 years, 433.3% more physical cores and 433.3% more threads, and a 340% more advanced lithography process.
The EPYC 9654 is our recommended choice as it beats the Xeon E5-2699 v3 in performance tests.
Should you still have questions on choice between Xeon E5-2699 v3 and EPYC 9654, ask them in Comments section, and we shall answer.
Similar processor comparisons
We picked several similar comparisons of processors in the same market segment and performance relatively close to those reviewed on this page.
