This site may earn affiliate commissions from the links on this folio. Terms of use.

There have been rumors of a new M1 processor practically since Apple kicked the M1 out the door. Today, Apple finally took the wraps off what it had planned. The M1 Pro and M1 Max pack a lot of firepower, at least equally far as specs are concerned. Nosotros'll see how they perform in the not-besides-distant future.

The M1 Pro packs upward to 10 CPU cores (8 high-performance, two high efficiency) and pairs it with upward to 16 GPU cores. In that location are 33.vii billion transistors in the product and the SoC offers 200GB/s of memory bandwidth across a 256-fleck memory omnibus. The viii high operation cores offer a total of 24MB of L2 cache, with a 192KB pedagogy cache and 128KB information caches. The data cache sizes for the M1 Pro and M1 Max are scaled up to match the increased core count.

The M1 Pro's GPU offers 2048 execution units in 16 graphics cores, with 5.2TFLOPs of processing and an 82 gigapixel fill rate. Nosotros'll have to wait for benchmarks to come across how well the onboard GPU scales, but Apple has some predictions of its ain (more on those soon):

The M1 Max is a 57 billion transistor SoC with a 32-core GPU, up to 64GB of onboard RAM, a 512-bit memory interface, 400GB/s of memory bandwidth, a 10-cadre CPU, upwardly to 32 GPU cores, and back up for four external displays. Apple tree is challenge that its new flake can outperform a Core i9 by 3x – 20x in machine learning performance.

The M1 Max's beefed-upward transistor count is largely spent on the GPU core, since the CPU core configuration is the same betwixt the two fries. Apple also predicts it can evangelize the equivalent performance of a 160W laptop in a 60W power envelope:

Apple-GPU-Perf

Overall, Apple states a 2.5x – 3x GPU functioning improvement at equivalent power. Apple'southward previous MacBook Pro systems used GPUs based on AMD's RDNA silicon, and while either Ampere or RDNA2 would probable score better, they wouldn't close a claimed 2.5x – 3x efficiency gap relative to RDNA. The visitor has pulled off a real improvement to overall efficiency if its benchmark figures prove true.

The M1 Pro and M1 Max double the maximum number of high operation cores and offer 3x – 4x the retentivity bandwidth depending on the model you choose. The retentivity loadout and loftier bandwidth are intended to keep the GPU fed. The implication of Apple'southward presentation is that its CPU and GPU efficiency are high enough that it can combine ii power-hungry parts together on the same silicon without taking a hefty power penalization.

We're not going to prejudge the CPUs before they can be tested, but Apple tree clearly believes information technology can keep scaling its CPUs until it replaces the entire x86 product line. The performance claims here are strong enough to still be impressive after accounting for typical corporate marketing and cherry-picked tests. Apple is essentially challenge that the M1 Pro and M1 Max tin can deliver far more performance in a mobile system than we've seen previously from any x86 CPU or SoC. The impact of translation software, where applicable, volition always verbal a penalty, but Apple has beefed up its SoC design a great bargain in simply 12 months. The M1 Pro and M1 Max are likely to threaten AMD, Intel, and Nvidia in markets that the original M1 CPU couldn't touch on and offering 8 high-performance cores puts the M1 Pro and M1 Max on par with the latest SoCs from AMD and Intel.

At present Read:

  • RISC vs. CISC Is the Wrong Lens for Comparing Modern x86, ARM CPUs
  • Microsoft Bleeds Market Share as Chromebooks Outsell Macs for the Showtime Time
  • The New Apple M1 Reviews Put AMD, Intel Officially on Observe