12-21-2024, 05:40 PM
I'm interested in what kind of uplift DDR5 might bring to the CPU-only Hash-Mode 15700 (Ethereum Wallet, SCRYPT). I noticed RAM speed can affect hash-rate, so if possible please include those specs as well.
I happened to run benchmark before enabling the XMP profile and was surprised at how much it affected hash-rate.
The same exact hardware ( Ryzen 9 5900X I have paired with 32GB DDR4):
XMP Profile disable (2133 MHz): 27 H/s
XMP Profile enabled (3600 MHz): 41 H/s
So that has me curious about DDR5 and hence this post. So anyone with a DDR5 and a few minutes, please share your benchmark.
Benchmark before enabling XMP Profile:
Benchmark after enabling XMP:
Thanks!
I happened to run benchmark before enabling the XMP profile and was surprised at how much it affected hash-rate.
The same exact hardware ( Ryzen 9 5900X I have paired with 32GB DDR4):
XMP Profile disable (2133 MHz): 27 H/s
XMP Profile enabled (3600 MHz): 41 H/s
So that has me curious about DDR5 and hence this post. So anyone with a DDR5 and a few minutes, please share your benchmark.
Code:
> hashcat -b -m 15700 -D 1 Benchmark before enabling XMP Profile:
Code:
PS C:\hashcat-6.2.6> .\hashcat.exe -b -m 15700 -D 1
hashcat (v6.2.6) starting in benchmark mode
Benchmarking uses hand-optimized kernel code by default.
You can use it in your cracking session by setting the -O option.
Note: Using optimized kernel code limits the maximum supported password length.
To disable the optimized kernel code in benchmark mode, use the -w option.
hiprtcCompileProgram is missing from HIPRTC shared library.
OpenCL API (OpenCL 2.1 AMD-APP (3628.0)) - Platform #1 [Advanced Micro Devices, Inc.]
=====================================================================================
* Device #1: AMD Radeon RX 6700 XT, skipped
OpenCL API (OpenCL 3.0 WINDOWS) - Platform #2 [Intel(R) Corporation]
====================================================================
* Device #2: AMD Ryzen 9 5900X 12-Core Processor, 16314/32693 MB (8173 MB allocatable), 24MCU
Benchmark relevant options:
===========================
* --opencl-device-types=1
* --optimized-kernel-enable
----------------------------------------------------------------
* Hash-Mode 15700 (Ethereum Wallet, SCRYPT) [Iterations: 262144]
----------------------------------------------------------------
Speed.#2.........: 27 H/s (1.49ms) @ Accel:24 Loops:1024 Thr:1 Vec:1
Started: Thu Nov 28 17:51:23 2024
Stopped: Thu Nov 28 17:51:27 2024Benchmark after enabling XMP:
Code:
PS C:\hashcat-6.2.6> .\hashcat.exe -b -m 15700 -D 1
hashcat (v6.2.6) starting in benchmark mode
Benchmarking uses hand-optimized kernel code by default.
You can use it in your cracking session by setting the -O option.
Note: Using optimized kernel code limits the maximum supported password length.
To disable the optimized kernel code in benchmark mode, use the -w option.
hiprtcCompileProgram is missing from HIPRTC shared library.
OpenCL API (OpenCL 2.1 AMD-APP (3628.0)) - Platform #1 [Advanced Micro Devices, Inc.]
=====================================================================================
* Device #1: AMD Radeon RX 6700 XT, skipped
OpenCL API (OpenCL 3.0 WINDOWS) - Platform #2 [Intel(R) Corporation]
====================================================================
* Device #2: AMD Ryzen 9 5900X 12-Core Processor, 16314/32693 MB (8173 MB allocatable), 24MCU
Benchmark relevant options:
===========================
* --opencl-device-types=1
* --optimized-kernel-enable
----------------------------------------------------------------
* Hash-Mode 15700 (Ethereum Wallet, SCRYPT) [Iterations: 262144]
----------------------------------------------------------------
Speed.#2.........: 41 H/s (0.98ms) @ Accel:24 Loops:1024 Thr:1 Vec:1
Started: Sat Dec 21 06:56:05 2024
Stopped: Sat Dec 21 06:56:14 2024Thanks!