benchmark9900k gains significantly with cache overclocking (my findings)
benchmark9900k gains significantly with cache overclocking (my findings)
I’ve checked my 9900k, it’s not ideal for aggressive overclocking. I tried cache-based overclocks again and the outcomes don’t match the usual “cache boost doesn’t help” claims online. Overclocking didn’t affect power consumption or heat much, and voltage only needed to rise slightly when adding more core with the cache. Here are the initial benchmark numbers:
- Aida64 Extreme CPU, Cache, FPU & RAM All Core, No AVX Offset Fixed Voltage
- Core/Cache Speed: 4.9 / 4.3
- Voltage: 1.28V
- Power Draw: 184W
- Temp: 72°C
- Core / Cache Speed: 4.9 / 4.7
- Voltage: 1.28V
- Power Draw: 189W
- Temp: 73°C
- Core / Cache Speed: 5.0 / 4.3
- Voltage: 1.35V
- Power Draw: 229W
- Temp: 90°C
- Cinebench R15 (Average of 10 runs):
- 4.9 GHz Core, 4.3 GHz Cache = 2073
- 5 GHz Core, 4.3 GHz Cache = 2133
- 4.9 GHz Core, 4.7 GHz Cache = 2204
- Cinebench R20 (Average of 10 runs):
- 4.9 GHz Core, 4.3 GHz Cache = 4919
- 5 GHz Core, 4.3 GHz Cache = 5105
- 4.9 GHz Core, 4.7 GHz Cache = 5192
- Game Benchmarks (Timespy):
- 4.9 GHz Core, 4.3 GHz Cache = 12,495 FPS
- 5 GHz Core, 4.3 GHz Cache = 12,219 FPS
- Project Cars:
- 5.0 / 4.3 = 139 FPS
- 4.9 / 4.7 = 147 FPS
- 4.9 / 4.7 = 98 FPS
- Witcher 3 (Average):
- 4.9 / 4.7 = 104 FPS
- 4.9 / 4.7 = 107 FPS
- Assassins Creed Odyssey:
- 4.9 / 4.7 = 105 FPS
- 5.0 / 4.3 = 115 FPS
- Arma III:
- 5.0 / 4.3 = 114 FPS
- Witcher 3 Low preset in Novigrad:
- 5.0 / 4.3 = 113 FPS
Overall, performance is solid but not exceptional. If you want better gains, consider lowering the clock speed by about 100MHz and boosting the cache until stability improves. This often reduces voltage needs and can prevent crashes or freezing.