EPYC 9355 vs EPYC 7642
Primary details
Comparing EPYC 7642 and EPYC 9355 processor market type (desktop or notebook), architecture, sales start time and price.
| Place in the ranking | 90 | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 5.56 | no data |
| Market segment | Server | Server |
| Series | AMD EPYC | no data |
| Power efficiency | 15.57 | no data |
| Architecture codename | Zen 2 (2017−2020) | Turin (2024) |
| Release date | 7 August 2019 (5 years ago) | 10 October 2024 (less than a year ago) |
| Launch price (MSRP) | $4,775 | $3,694 |
Cost-effectiveness evaluation
Performance per price, higher is better.
Detailed specifications
EPYC 7642 and EPYC 9355 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 | 48 (Octatetraconta-Core) | 32 (Dotriaconta-Core) |
| Threads | 96 | 64 |
| Base clock speed | 2.4 GHz | 3.55 GHz |
| Boost clock speed | 3.4 GHz | 4.4 GHz |
| Multiplier | 23 | no data |
| L1 cache | 96K (per core) | 80 KB (per core) |
| L2 cache | 512K (per core) | 1 MB (per core) |
| L3 cache | 256 MB (shared) | 256 MB (shared) |
| Chip lithography | 7 nm, 14 nm | 4 nm |
| Die size | 192 mm2 | 8x 70.6 mm2 |
| Number of transistors | 4,800 million | 66,520 million |
| 64 bit support | + | + |
| Windows 11 compatibility | + | no data |
| Unlocked multiplier | + | - |
Compatibility
Information on EPYC 7642 and EPYC 9355 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 (Multiprocessor) | 2 |
| Socket | TR4 | SP5 |
| Power consumption (TDP) | 225 Watt | 280 Watt |
Technologies and extensions
Technological solutions and additional instructions supported by EPYC 7642 and EPYC 9355. You'll probably need this information if you require some particular technology.
| AES-NI | + | + |
| AVX | + | + |
| Precision Boost 2 | + | + |
Virtualization technologies
Virtual machine speed-up technologies supported by EPYC 7642 and EPYC 9355 are enumerated here.
| AMD-V | + | + |
Memory specs
Types, maximum amount and channel quantity of RAM supported by EPYC 7642 and EPYC 9355. Depending on the motherboard, higher memory frequencies may be supported.
| Supported memory types | DDR4 Eight-channel | DDR5 |
| Maximum memory size | 4 TiB | no data |
| Max memory channels | 8 | no data |
| Maximum memory bandwidth | 204.763 GB/s | no data |
| ECC memory support | + | - |
Graphics specifications
General parameters of integrated GPUs, if any.
| Integrated graphics card | no data | N/A |
Peripherals
Specifications and connection of peripherals supported by EPYC 7642 and EPYC 9355.
| PCIe version | no data | 5.0 |
| PCI Express lanes | no data | 128 |
Pros & cons summary
| Recency | 7 August 2019 | 10 October 2024 |
| Physical cores | 48 | 32 |
| Threads | 96 | 64 |
| Chip lithography | 7 nm | 4 nm |
| Power consumption (TDP) | 225 Watt | 280 Watt |
EPYC 7642 has 50% more physical cores and 50% more threads, and 24.4% lower power consumption.
EPYC 9355, on the other hand, has an age advantage of 5 years, and a 75% more advanced lithography process.
We couldn't decide between EPYC 7642 and EPYC 9355. We've got no test results to judge.
Should you still have questions on choice between EPYC 7642 and EPYC 9355, 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.
