Friday, October 6th 2023

Intel Lunar Lake Processor Appears in SiSoftware Sandra Benchmark

Intel's next-generation Lunar Lake processor has appeared in the SiSoftware Sandra benchmarking suite, and the online database has revealed many details, thanks to a spotting by @Olrak29 of X/Twitter. Considering Intel's Meteor Lake is still two months away from its launch, the presence of Lunar Lake's benchmarks is indeed intriguing. Interestingly, Intel showcased a Lunar Lake laptop at the Intel Innovation 2023 event, and this SiSoft entry might be related to that demo. The data from SiSoft details the system as a "Genuine Inte l(R) 0000 1.00 GHz (5M 20c 3.91 GHz + 2.61 GHz, 3.3 GHz IMC, 4x 2.5 MB + 4 MB L2, 2x 8 MB L3)," hinting at a "Lunar Lake Client System (Intel LNL-M LP5 RVP1)." Deciphering these details, the Lunar Lake system adopts a 4+4 core configuration, utilizing a mix of Lion Cove and Skymont architecture cores tailored for performance and efficiency.

Moreover, the benchmark report pegs this CPU as a low-power laptop variant with a 17 W TDP. While it operates at a 1.0 GHz base frequency, it reached a speed of 3.91 GHz during the testing. However, these numbers should be taken cautiously since it's likely an engineering sample. Cache details are outlined, suggesting a 2.5 MB L2 cache per P-core, an added 4 MB L2 cache for E-cores, and a 16 MB L3 cache. No details on the integrated GPU were revealed, although it's anticipated that Lunar Lake will house Intel's Xe2-LPG graphics and LPDDR5 system memory. Intel has shared that Lunar Lake is scheduled for a 2024 release in mobile/laptop devices, targeting performance-per-watt leadership. Arrow Lake processors, catering to desktops, might share the core architecture and are anticipated to launch around the same timeframe.
Sources: SiSoftware Sandra, via Olrak29 (X/Twitter)
Add your own comment

7 Comments on Intel Lunar Lake Processor Appears in SiSoftware Sandra Benchmark

#1
Minus Infinity
Arrow Lake will also be launched in mobile form, but not until sometime in 2025. Luna Lake is some stand alone low power APU, not even a replacement for Meteor Lake
Posted on Reply
#2
Jism
Tell me why the AI thing is pushed to much in consumer hardware now?
Posted on Reply
#3
Minus Infinity
JismTell me why the AI thing is pushed to much in consumer hardware now?
Becuase there's plenty of software now using AI eg Photohop and the NN chip can accelerate generative fill etc. Like it or not AI isn't going anywhere.
Posted on Reply
#4
Nike_486DX
Too many Lakes lately, and by the time intel comes out with true 3nm, the competition will already be at sub 1nm node :laugh:
Posted on Reply
#5
Minus Infinity
Nike_486DXToo many Lakes lately, and by the time intel comes out with true 3nm, the competition will already be at sub 1nm node :laugh:
Well TSMC and Samsung are struggling with 3nm and who cares what the "size" label is, it's how it actually performs. If Intel can make a node that competes with TSMC's latest and greatest I don't really care what "feature" size is used.
Posted on Reply
#6
Prima.Vera
Nike_486DXToo many Lakes lately, and by the time intel comes out with true 3nm, the competition will already be at sub 1nm node :laugh:
There is no such thing as a true 3nm. This have been a bs measurement for long time now. TSMC should be held accountable for ruining the actual measurement.
We can laugh as much as we want at Intel 14nm+++++++++ process, but at least they kept the size (sourt of) real, by improving the process with each iteration. While Samsung and especially TSMC start to throw in numbers out of their pockets, even if there process was same or worst than Intel's latest.
Posted on Reply
#7
Nike_486DX
Minus InfinityWell TSMC and Samsung are struggling with 3nm and who cares what the "size" label is, it's how it actually performs. If Intel can make a node that competes with TSMC's latest and greatest I don't really care what "feature" size is used.
i mean power efficiency, and right now i9 13900k struggles against 7950X, same level of performance but intel draws +100w just because its using older tech. For the very same reason they could only fit 8 performance cores, because fitting 16 would result in a huge silicon die, and insane power draw that a 360mm aio would struggle with even at stock clocks. Reminds me of the FX days, only now its intel haha. Bad thing is that amd would most likely slow down their innovations a bit, because they already been ahead of intel for a while.
Posted on Reply
May 21st, 2024 18:01 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts