Intel Core i9-13900 test results emerge
A preview of the upcoming Intel 13th Gen Core CPU called Core i9-13900 has been published over at SiSoftware.
One should note that this is not a typical review based on actual hardware testing, but rather, an aggregation of existing results in the SiSoftware Sandra database. Therefore, it should be considered an overview of the upcoming architecture with elements of actual performance testing.
Intel Core i9-13900 is a 24-core processor with 8 Performance and 16 Efficient cores. According to the SiSoftware, this processor series is based on an updated Intel 7+ process technology, has 20% larger L3 cache and supports faster DDR5 memory up to 5600 MT/s (up from 4800 MT/s on Alder Lake).
Furthermore, L2 cache has been improved for Raptor Lake, now twice as big for Performance and Efficient cores (2MB per core for big core and 4MB per cluster of 4 cores on small cores). What is now missing on Raptor Lake silicon is AVX-512 support now completely disabled (or not even present) on the silicon.
Alleged Intel Core i9-13900 Engineering Sample CPU Performance, Source: SiSoftware
In test ALU/FPU test results collected by the author of this preview an overall 33% to 50% improvement over Alder Lake is demonstrated. Notably, that’s with lower clock speeds: Raptor Lake at 3.7 GHz P-Core & 2.76 GHz E-Core vs Alder Lake at 5.0 GHz P-Core & 3.8 GHz E-Core. Meanwhile, vectorized/SIMD tests confirm 5% to 8% better performance than Alder Lake.
Intel 13th Gen Core desktop processors should launch in a few months time. Various sources claim it is either ‘a month before‘ NVIDIA GeForce RTX 40 series (so possibly in August) or October.
| Tested Processors by SiSoftware | |||||
|---|---|---|---|---|---|
| Specifications | Intel Core i9-13900 8C+16c/32T (RPL) | Intel Core i9-12900 8C+8c/24T (ADL) | Intel Core i9-11900K 8C/16T (RKL) | AMD Ryzen 9 5900X 12C/24T (Zen3) | Comments |
| Arch(itecture) | Raptor Cove + Gracemont / RaptorLake | Golden Cove + Gracemont / AlderLake | Cypress Cove / RocketLake | Zen3 / Vermeer | The very latest arch |
| Cores (CU) / Threads (SP) | 8C+16c / 32T | 8C+8c / 24T | 8C / 16T | 2M / 12C / 24T | 8 more LITTLE cores |
| Rated Speed (GHz) | ? | 2.4 big / 1.8 LITTLE | 3.5 | 3.7 | To be confirmed |
| All/Single Turbo Speed (GHz) | 3.7 big / 2.76 LITTLE | 5.0 big / 3.8 LITTLE | 4.8 – 5.3 | 4.5 – 4.8 | To be confirmed |
| Rated/Turbo Power (W) | 65 – 200 [=] | 65 – 200 | 125 – 228 | 105 – 135 | TDP/Turbo same but huge overall |
| L1D / L1I Caches | 8x 48kB/32kB + 16x 64kB/32kB | 8x 48kB/32kB + 8x 64kB/32kB | 8x 48kB 12-way / 8x 32kB 8-way | 12x 32kB 8-way / 12x 32kB 8-way | Same L1D/L1I caches |
| L2 Caches | 8x 2MB + 4x 4MB (32MB) [+2.3x] | 8x 1.25MB + 2x 2MB (14MB) | 8x 512kB 16-way (4MB) | 12x 512kB 16-way (6MB) | L2 is over 2x larger! |
| L3 Cache(s) | 36MB 16-way [+20%] | 30MB 16-way | 16MB 16-way | 2x 32MB 16-way (64MB) | L3 is 20% larger |
| Microcode (Firmware) | TBA | 090672-1E | 06A701-40 | 8F7100-1009 | Revisions just keep on coming. |
| Special Instruction Sets | VNNI/256, SHA, VAES/256 | VNNI/256, SHA, VAES/256 | AVX512, VNNI/512, SHA, VAES/512 | AVX2/FMA, SHA | AVX512 still MIA |
| SIMD Width / Units | 2x 256-bit | 2x 256-bit | 512-bit (1x FMA) | 2x 256-bit | Same SIMD units |
| Price / RRP (USD) | $549? | $519 | $539 | $549 | Price is a little higher? |
Source: SiSoftware
