FR
AMD EPYC 7742 vs AMD EPYC 9654
Comparison of the technical characteristics between the processors, with the AMD EPYC 7742 on one side and the AMD EPYC 9654 on the other side. The first is dedicated to the server sector, It has 64 cores, 128 threads, a maximum frequency of 3.4GHz. The second is used on the server segment, it has a total of 96 cores, 192 threads, its turbo frequency is set to 3.6 GHz. The following table also compares the lithography, the number of transistors (if indicated), the amount of cache memory, the maximum RAM memory capacity, the type of memory accepted, the release date, the maximum number of PCIe lanes, the values obtained in Geekbench 4 and Cinebench R15.
Note: Commissions may be earned from the links above.
This page contains references to products from one or more of our advertisers. We may receive compensation when you click on links to those products. For an explanation of our advertising policy, please visit this page.
Specification comparison:
| Processor | AMD EPYC 7742 | AMD EPYC 9654 | ||||||
| Market (main) | Server | Server | ||||||
| ISA | x86-64 (64 bit) | x86-64 (64 bit) | ||||||
| Microarchitecture | Zen 2 | Zen 4 | ||||||
| Core name | Rome | Genoa | ||||||
| Family | EPYC 7002 | EPYC 9004 | ||||||
| Part number(s), S-Spec | 100-000000053, 100-100000053WOF |
100-000000789, 100-100000789WOF |
||||||
| Release date | Q3 2019 | Q4 2022 | ||||||
| Lithography | 7 nm | 5 nm | ||||||
| Transistors | 32,000,000,000 | - | ||||||
| Cores | 64 | 96 | ||||||
| Threads | 128 | 192 | ||||||
| Base frequency | 2.3 GHz | 2.4 GHz | ||||||
| Turbo frequency | 3.4 GHz | 3.6 GHz | ||||||
| High performance cores | - |
96 Cores 192 Threads @ 2.4 / 3.55 GHz |
||||||
| Cache memory | 256 MB | 384 MB | ||||||
| Max memory capacity | 4 TB | 6 TB | ||||||
| Memory types | DDR4-3200 |
DDR5-4800 |
||||||
| Max # of memory channels | 8 | 12 | ||||||
| Max memory bandwidth | 190.7 GB/s | 460.8 GB/s | ||||||
| Max PCIe lanes | 128 | 128 | ||||||
| TDP | 225 W | 360 W | ||||||
| Suggested PSU | 750W ATX Power Supply  |
900W ATX Power Supply |
||||||
| GPU integrated graphics | None | None | ||||||
| Socket | SP3, LGA-4094 | SP5 | ||||||
| Compatible motherboard | Socket SP3 Motherboard |
Socket SP5 Motherboard |
||||||
| Crypto engine | - |
Advanced Encryption Standard instructions |
||||||
| Security | - |
Enhanced Virus Protection, Secure Memory Encryption |
||||||
| PassMark single thread | 2,163 | 2,881 | ||||||
| PassMark CPU Mark | 69,774 | 124,127 | ||||||
| (Linux) Geekbench 5 single core | 1,004 | 1,530 | ||||||
| (Linux) Geekbench 5 multi-core | 40,933 | 75,932 | ||||||
| Amazon |  |
|
||||||
| eBay |  |
|
Note: Commissions may be earned from the links above.
We can better compare what are the technical differences between the two processors.
Suggested PSU: We assume that we have An ATX computer case, a high end graphics card, 16GB RAM, a 512GB SSD, a 1TB HDD hard drive, a Blu-Ray drive. We will have to rely on a more powerful power supply if we want to have several graphics cards, several monitors, more memory, etc.
Price: For technical reasons, we cannot currently display a price less than 24 hours, or a real-time price. This is why we prefer for the moment not to show a price. You should refer to the respective online stores for the latest price, as well as availability.
The processor AMD EPYC 9654 has a larger number of cores, the turbo frequency of AMD EPYC 9654 is bigger, that the PDT of AMD EPYC 7742 is lower. The AMD EPYC 9654 was started more recently.
Performance comparison with the benchmarks:
Performance comparison between the two processors, for this we consider the results generated on benchmark software such as Geekbench 4.
| PassMark - CPU Mark & single thread | |
|---|---|
| AMD EPYC 9654 |
2,881 124,127 |
| AMD EPYC 7742 |
2,163 69,774 |
In single core, the difference is 33%. In multi-core, the difference in terms of gap is 78%.
Note: Commissions may be earned from the links above. These scores are only an
average of the performances got with these processors, you may get different results.
average of the performances got with these processors, you may get different results.
PassMark is a benchmarking software that performs several performance tests including prime numbers, integers, floating point, compression, physics, extended instructions, encoding, sorting. The higher the score is, the higher is the device capacity.
On Windows:
| Geekbench 5 - Multi-core & single core score - Windows | |
|---|---|
| AMD EPYC 9654 |
1,085 24,398 |
| AMD EPYC 7742 |
975 16,886 |
In single core, the difference is 11%. In multi-core, the difference in terms of gap is 44%.
On Linux:
| Geekbench 5 - Multi-core & single core score - Linux | |
|---|---|
| AMD EPYC 9654 |
1,530 75,932 |
| AMD EPYC 7742 |
1,004 40,933 |
In single core, the difference is 52%. In multi-core, the difference in terms of gap is 86%.
Note: Commissions may be earned from the links above. These scores are only an
average of the performances got with these processors, you may get different results.
average of the performances got with these processors, you may get different results.
Geekbench 5 is a software for measuring the performance of a computer system, for fixed devices, mobile devices, servers. This platform makes it possible to better compare the power of the CPU, the computing power and to compare it with similar or totally different systems. Geekbench 5 includes new workloads that represent work tasks and applications that we can find in reality.
Equivalence:
AMD EPYC 7742 Intel equivalentAMD EPYC 9654 Intel equivalentSee also:
Dual AMD EPYC 7742Dual AMD EPYC 9654
Disclaimer:
When you click on links to various merchants on this site and make a purchase, this can result in this site earning a commission. Affiliate programs and affiliations include, but are not limited to, the eBay Partner Network.
As an Amazon Associate I earn from qualifying purchases.
This page includes affiliate links for which the administrator of GadgetVersus may earn a commission at no extra cost to you should you make a purchase. These links are indicated using the hashtag #ad.
Information:
We do not assume any responsibility for the data displayed on our website. Please use at your own risk. Some or all of this data may be out of date or incomplete, please refer to the technical page on the respective manufacturer's website to find the latest up-to-date information regarding the specifics of these products.