Support NeoGAF

[tusharngf]

Intel's Raptor Lake Desktop CPUs launch later this year to tackle AMD's Zen 4 'Raphael' lineup and it looks like SiSoftware has once again managed to publish a mini-review of a Core i9-13900 CPU with 24 cores and 32 threads in an early engineering state against Intel's Alder Lake & AMD Zen 3 chips.

Intel Raptor Lake Core i9-13900 ES CPU Up To 50% Faster Than Alder Lake Core i9-12900 At a Low Clock Speed of 3.7 GHz​

The 13th Gen Intel Raptor Lake CPUs will be combing the new Raptor Cove P-Cores and Gracemont (E-Cores) in an optimized 10nm (Intel 7+) package. Compared to Intel's Alder Lake CPUs, the Raptor Lake chips will come with a host of improvements besides just more cores and clock speeds. These include:

• Support for up to DDR5-5600 memory (JEDEC)
• 20% Larger L3 cache (Up To 36 MB Unified)
• 2x Larger L2 cache (Up To 32 MB)
• Support For AVX/AVX2 on E-Cores
• No Support For AVX-512 (Just Like Alder Lake-S)

The Raptor Lake CPU sample tested is an Intel Core i9-13900 which features 8 P-Cores and 16 E-Cores for a total of 24 cores and 32 threads. The chip was running at max clock speeds of 3.7 GHz for the P-Cores and 2.76 GHz for the E-Cores. That's really low from the retail version which will be offering over 5.5 GHz speeds as mentioned in various leaks. The CPU is equipped with 32 MB of L2 cache (8 x 2 MB for P-Cores / 4 x 4 MB for E-Cores) and 36 MB of L3 cache for a combined total of 68 MB of 'Gaming' cache.

Coming to the benchmarks, it is not mentioned what exact test setup was used and if the memory was indeed running at DDR5-5600 speeds. But with that said, the results are very impressive for an ES chip with such low clock speeds. The Intel Core i9-13900 'Raptor Lake' CPU offered up to 50% uplift over the Intel Core i9-12900 in Whetstone FP32 tests and an impressive 2x gain in the FP64 tests. The chip ended up faster than both, the Intel Core i9-12900 and AMD Ryzen 9 5900X which is good for the upcoming lineup.

Intel Raptor Lake Core i9-13900 Leaked Benchmarks (Credits: SiSoftware)​

Native Benchmarks	Intel Core i9-13900 8C+16c/32T big+LITTLE (RPL)	Intel Core i9-12900 8C+8c/24T big+LITTLE (ADL)	Intel Core i9-11900K 8C/16T (RKL)	AMD Ryzen 9 5900X 12C/24T (Zen3)	AMD Ryzen 9 5900X 12C/24T (Zen3)
Native Dhrystone Integer (GIPS)	619 [+33%]	464	545	589	RPL is 33% faster than ADL
Native Dhrystone Long (GIPS)	648 [+34%]	485	551	594	A 64-bit integer workload RPL is 34% faster.
Native FP32 (Float) Whetstone (GFLOPS)	500 [+49%]	336	285	388	With floating-point, RPL is 50% faster
Native FP64 (Double) Whetstone (GFLOPS)	388 [+2x]	191	239	324	With FP64 RPL is 2x faster!
Native Integer (Int32) Multi-Media (Mpix/s)	1,945 [-7%]	2092	2000	2840	RPL is 7% slower than ADL here.
Native Long (Int64) Multi-Media (Mpix/s)	730 [+4%]	705	608	919	With a 64-bit, RPL is 4% faster.
Native Quad-Int (Int128) Multi-Media (Mpix/s)	138 [+8%]	128	160	173	Using 64-bit int to emulate Int128 RPL is 8% faster.
Native Float/FP32 Multi-Media (Mpix/s)	2,180 [+4%]	2089	1620	2000	In this floating-point vectorised test RPL is 4% faster
Native Double/FP64 Multi-Media (Mpix/s)	1,116 [+5%]	1063	806	1270	Switching to FP64 RPL is 5% faster
Native Quad-Float/FP128 Multi-Media (Mpix/s)	53 [+6%]	50	35.74	53.16	Using FP64 to mantissa extend FP128 RPL is 6

Full article : https://wccftech.com/intel-raptor-l...n-alder-lake-core-i9-12900-leaked-benchmarks/

 

[MikeM]

Cool. More interested in 13400 and 13600 chips.

 

[ACESHIGH]

How many FX6300 duck taped together?

 

[sachos]

Big CPU gains, big PC emulation benefits, looking at you RPCS3.

 

[StateofMajora]

Right on. Beat amd for the sake of competition.

And for my portfolio

 

[palpabl_purpura]

It's going to be close to 1g for this thing. Look at the 12900ks.

 

[GreatnessRD]

Patty Boy said he got smoke for Su Bae. Let the back and forth commence, folks.

 

[kikkis]

What's the point on avx 512 on amd if even Intel doesn't have it.