Intel's latest Arrow Lake CPU firmware reportedly offers little to no performance gains — users test the microcode ahead of launch on the ASRock Z890 Taichi OCF

Arrow Lake
(Image credit: Intel)

The 0x114 microcode for Intel's Core Ultra 200S (Arrow Lake) processor lineup has surfaced online at Overclock.net. This patch is believed to address the significant performance gaps.

However, forum users report negligible gains in performance. It is important to note that motherboard vendors have yet to officially release this microcode, which is apparent because it is not listed on any partner's support page as of this writing.

Arrow Lake suffers from hefty latency penalties stemming from inherent architectural flaws. Since the memory controller is off-die on the SoC Tile, gaming performance takes a serious hit due to abysmal L3 access cycles. Leaks suggest that Intel's Core Ultra 300 or Panther Lake CPUs might reintegrate the IMC into the CPU Tile. Nonetheless, Intel acknowledged these issues last month and promised a fix by early December through OS-level updates and BIOS patches.

Rumor has it that the upcoming 0x114 microcode is the long-awaited one-stop fix for Arrow Lake, which has leaked online. While we don't recommend flashing microcodes from third-party sources, a few brave souls at Overclock.net did that just for experimentation, and to their dismay, the gains were non-existent. As a user reported, his Core Ultra 9 285K paired with the ASRock Z890 Taichi OCF saw a 6% drop in Cinebench R23 MT scores because of low clock speeds.

Yesterday, Cyberpunk 2077 received a new update that offered up to 33% better performance on Intel's Core Ultra 200S processors. In the same forum, a user linked two benchmarks running a custom scene in Cyberpunk 2077 (1,2) and claimed an additional 3% gain in FPS with a 10% lower power draw - the validity of which we cannot verify.

As motherboard vendors still offer the older 0x113 microcode, let's wait for the official release before jumping to conclusions. The supposedly lackluster gains could be attributed to the limited testing data, or the microcode doesn't offer much. Since we're almost halfway through December - past Intel's deadline - expect a release in the form of a stable or beta BIOS update in a couple of days.

Hassam Nasir
Contributing Writer

Hassam Nasir is a die-hard hardware enthusiast with years of experience as a tech editor and writer, focusing on detailed CPU comparisons and general hardware news. When he’s not working, you’ll find him bending tubes for his ever-evolving custom water-loop gaming rig or benchmarking the latest CPUs and GPUs just for fun.

  • Americanrust
    Why post unverified crap?
    Reply
  • dalek1234
    I said this before. Intel fix will do very little (or nothing) to address the issue. Promised fix is just PR lie, so no surprise the fix is useless.
    Reply
  • magbarn
    Desperate Intel needed a Core 2 Duo chip level of performance improvement and instead gave us Bulldozer 2.0
    Reply
  • endocine
    The only cadence intel has is releasing ever worsening products.
    Reply
  • Mama Changa
    Arrow to the face Lake is going to be an Albatross around Intel's neck. Panther Lake can't come fast enough and I fully anticipate the once mobile only chip will now be heading for desktop rather than a lame Arrow Lake refresh.

    Maybe Intel should get CD Red Projekt to do the fw update.
    Reply
  • cyrusfox
    Mama Changa said:
    Arrow to the face Lake is going to be an Albatross around Intel's neck. Panther Lake can't come fast enough and I fully anticipate the once mobile only chip will now be heading for desktop rather than a lame Arrow Lake refresh.

    Maybe Intel should get CD Red Projekt to do the fw update.
    This is really revealing why meteor was Mobile only... But I am hopeful microcode fixes will smooth out and eliminate the worst cases of latency. But with this being the first chiplet desktop chip, I do think some of this is unavoidable.
    Reply
  • magbarn
    cyrusfox said:
    This is really revealing why meteor was Mobile only... But I am hopeful microcode fixes will smooth out and eliminate the worst cases of latency. But with this being the first chiplet desktop chip, I do think some of this is unavoidable.
    You mean Intel's first chiplet desktop chip. What I found remarkable is that they still bothered to release such a bad chip. Simulations and prototypes should've shown its failure. The old Intel 15 years ago would've done a TSMC 3 respin of the much better Raptor Lake (like Sandy to Ivy Bridge) while working on improving Arrow Lake.
    Reply
  • Pigpig
    i think this firmware update is fixing gaming performance bug related to variable voltage issue, so it can see the performance boost in Gaming FPS, but cannot see the improvement in testing benchmark.
    Reply