Intel Meteor Lake Analysis - Core Ultra 7 155H only convinces with GPU performance
Intel just announced the new 14th Gen mobile processors with the code name Meteor Lake, which introduce some significant changes including the naming scheme. The familiar Core i5 and Core i7 chips are now called Core Ultra 5 and Core Ultra 7. Intel also drops the P-series line-up, which was mainly used for the 28W class in the previous two generations. As it was in previous years, you now once again have the choice between U-series models and H-series models, which cover a very wide TDP range. We had the chance to test the new Intel Core Ultra 7 155H, which is the direct successor to the popular Core i7-13700H, before the official launch. There are also major technical changes that we will cover in the following sections.
Overview Intel Core Ultra-H & Intel Core Ultra-U
We want to start with an overview of the new mobile processor line-up since there are some changes. There are basically two types, the Core Ultra U models with a TDP between 15-57 Watts as well as the Core Ultra H chips with a TDP between 28-115 Watts. This means the U-series stays in the same range as before, while the new H-series now replaces the former Raptor Lake-P models like the Core i7-1360P as well as the Raptor Lake-H45 chips like the Core i7-13700H or the Core i9-13900H.
All new processors offer a total of 10 efficiency cores (more on that shortly), only the number of performance cores differs depending on the model. Th high-end chips Core Ultra 155H, Core Ultra 7 165H as well as the Core Ultra 9 185H have 6 fast performance cores, which is similar to the previous H45 processors like the Core i7-13700H. These three new CPUs offer a total of 16 cores/22 threads. The two new models Core Ultra 5 135J and Core Ultra 5 125H only have 4 performance cores, so the are pretty much the direct successors to Raptor Lake-P chips like the Core i7-1360P. All new H-series models also get the new Arc GPU with 8 Xe cores (Core Ultra 7 & Core Ultra 9) or 7 Xe cores (Core Ultra 5).
The regular U-series chips as well as the H-series models can be equipped with up to 64 GB LPDDR5/x-7467-RAM or up to 96 GB DDR5-5600 RAM. There will be two more U-series chips in 2024 with a lower TDP range between 9-30 Watts and they are also equipped with slower LPDDR5x-6400 RAM. All new Core Ultra mobile processor are also equipped with a dedicated NPU (neural Processor) with two Gen3 Neural Compute Engines.
Specs - Meteor Lake w/ chiplet design and 7 nm compute tile
The major design change of the Meteor Lake processors is the switch from a monolithic design to a chiplet/tile design, where the chip consists of multiple parts. There are certain advantages to this approach, including better scaling capabilities and not all of the tiles have to be manufactured on the same node. Meteor Lake consists of four different tiles: SoC tile as the main component with all the basic functionality, compute tile with P- and E-cores, GPU tile as well as an I/O tile. The compute tile is manufactured in the new Intel4 process, so it is Intel’s first 7 nm chip. All the other tiles are manufactured by TSMC (SoC & I/O tile: TSMC N6, GPU tile: TSMC N5). The chiplet design also results in a slightly higher power consumption though.
The key part of the new processor is the SoC tile, which includes all important functionalities and even two dedicated LowPower efficiency cores. It also includes the media engine as well as the display engine and the new NPU is located here as well. This means basic tasks can be handled without activating the compute or GPU tiles, which saves power. Intel advertises that idle scenarios and even stuff like Netflix streaming can be handled by the SoC tile alone. We obviously have to test this by ourselves, but we doubt the two efficiency cores are sufficient when there are also some background tasks.
The compute tile of the new Meteor Lake chips is the first chip manufactured in the Intel4 process (7 nm). It consists of 2-6 performance cores (Redwood Cove) as well as 8 efficiency cores (Crestmont) with improved efficiency. The new GPU tile consists of 4, 7 or 8 Xe cores and Intel also uses different designations. The 4-core GPU of the U-series chips is simply called Intel Graphics, while the 7 or 8-core versions of the H-series are called Intel Arc GPU. In addition to the dedicated NPU in the SoC tile, the two compute and GPU tiles can be used for AI workloads as well, depending on the requirements.
Test Systems
We had the opportunity to test the new Meteor Lake Core Ultra 7 155H in two laptops: the new Asus ZenBook 14 and the new Acer Swift Go 14. We want to mention that both products were not final retail units, so there might be some software and driver optimizations until they are shipped to customers. The TDP of the Acer Swift Go 14 was set to 55/45 Watts and 50/33 Watts for the Asus ZenBook 14. We were limited to the Acer Swift Go 14 for our power consumption measurements. Both laptops were equipped with 32 GB LPDDR5x-7467 RAM and the GPU driver was version 31.0.101.5122. The in-depth review of the new Acer Swift Go 14 will be published soon.
Review Procedure
In order to get a meaningful comparison between the different processor and graphics adapters, we look at the performance results in synthetic benchmarks, but also the power consumption, which results in the efficiency. All the power measurements were performed with an external screen, so we can eliminate different panel types that would distort the results. Keep in mind that we measure the power consumption of the whole system and do not solely rely on the displayed values for the CPU and GPU consumption.
Single-Core Performance & Efficiency
We already mentioned that the underlying architecture did not change, but it was further refined according to Intel. We were quite surprised that the single-core performance is actually a bit lower compared to the previous Raptor Lake chips. The new Core Ultra 7 155H is closer to the AMD’s current Zen4 processors instead, but the new Meteor Lake chip is clearly beaten by Apple’s M3 generation and also Qualcomm’s Snapdragon X Elite. Our results are pretty much on par with the reference scores from Intel, so the single-core performance is roughly the same.
Cinebench 2024 / CPU Single Core | |
Apple M3 Pro 12-Core | |
Qualcomm Snapdragon X Elite | |
Qualcomm Snapdragon X Elite | |
Intel Core Ultra 7 155H | |
AMD Ryzen 7 7840S | |
Intel Core Ultra 7 155H |
The resulting single-core efficiency is also pretty sobering, since the new Acer Swift Go 14 with the Core Ultra 7 155H is actually slightly worse compared to the Core i7-1360P ad the Core i7-13700H. However, we can also see that the CPU package power during Cinebench R23 Single is noticeably higher compared to the ZenBook 14, but we unfortunately have no power measurements for the Asus at this point. Looking at the numbers, the device would be roughly on par with the two Core i7-13700H models. We already mentioned this is not a final retail unit, so the results might improve. We will update this article accordingly once we get our hands on final products.
Power Consumption / Cinebench R23 Single Power Efficiency - external Monitor | |
Apple M3 Pro 12-Core | |
AMD Ryzen 7 7840U | |
AMD Ryzen 9 PRO 7940HS | |
Intel Core i7-13700H | |
Intel Core i7-13700H | |
AMD Ryzen 7 7840S | |
Intel Core i7-1360P | |
Intel Core Ultra 7 155H |
Power Consumption / Cinebench R23 Single (external Monitor) | |
Intel Core Ultra 7 155H | |
Intel Core i7-1360P | |
Intel Core i7-13700H | |
AMD Ryzen 7 7840S | |
Intel Core i7-13700H | |
AMD Ryzen 9 PRO 7940HS | |
AMD Ryzen 7 7840U | |
Apple M3 Pro 12-Core |
* ... smaller is better
Multi-Core Performance & Efficiency
Our multi-core tests show performance gains and the best comparison processor is the Core i7-13700H, which also offers 6 performance cores for a total of 20 threads. The Core i7-1360P on the other hand only has 4 performance cores (16 threads) and we have shown multiple times that the Core i7-1360P in slower than the Core i7-13700H at 40 Watts. The Core Ultra 7 155H has two more efficiency cores (total of 22 threads), so it is not surprising that the multi-core performance is slightly better. However, the performance depends on the power limits and the two units with the Core Ultra 7 155H are slightly faster than the Core i7-13700H in the Schenker Vision 14 (45/40 Watts), but slower than the Core i7-13700H in the Microsoft Surface Laptop Studio 2 (82/50 Watts). The Core Ultra 7 155H can operate in a TDP range between 28-115 Watts, so the actual multi-core performance will vary heavily between different laptops.
The multi-core efficiency for our review unit of the Acer Swift Go 14 is better than Raptor Lake, but the advantage over the Core i7-1360P and Core i7-13700H is not that great with 3 up to 11 %. This means Intel is still far behind AMD Zen4 and Apple’s M3 generation.
Power Consumption / Cinebench R23 Multi Power Efficiency - external Monitor | |
Apple M3 Pro 11-Core | |
Apple M3 | |
AMD Ryzen 7 7840U | |
Apple M3 Pro 12-Core | |
Apple M3 Max 16-Core | |
AMD Ryzen 9 PRO 7940HS | |
AMD Ryzen 7 7840S | |
Intel Core Ultra 7 155H | |
Intel Core i7-13700H | |
Intel Core i7-1360P | |
Intel Core i7-13700H |
Power Consumption / Cinebench R23 Multi (external Monitor) | |
Intel Core i7-13700H | |
Intel Core Ultra 7 155H | |
Apple M3 Max 16-Core | |
Intel Core i7-13700H | |
Intel Core i7-1360P | |
AMD Ryzen 7 7840S | |
AMD Ryzen 9 PRO 7940HS | |
Apple M3 Pro 12-Core | |
Apple M3 Pro 11-Core | |
AMD Ryzen 7 7840U | |
Apple M3 |
* ... smaller is better
GPU Performance & Efficiency
Intel claims the GPU performance of the new Arc GPU with 8 Xe cores (128 EUs) has doubled compared to the old Iris Xe Graphics G7 (96 EUs), and we can confirm that claim, at least roughly. This means the new Arc GPU is also faster than AMDs Radeon 780M of the Zen4 CPUs. The two dedicated Intel GPUs Arc A350M and Arc A370M are also beaten, but Apple’s M3 GPUs are more powerful. The Core Ultra 5 chips of the H-series will be equipped with a slower 7-core Arc GPU, which will be closer to the Radeon 780M or even slightly slower.
So far, we do not have any numbers for the new Core Ultra U-models with the new Intel Graphics, but considering it only has four Xe cores with lower maximum clocks, we assume the performance will be down by around 50 %. This means this new GPU called Intel Graphics could be pretty much on the same performance level as the old Iris Xe Graphics G7 (96 EUs).
The big advantage of the synthetic benchmarks is not confirmed in our gaming tests so far, but upcoming driver updates can change the situation noticeably. The best-case scenario so far is that the performance is on par with the Radeon 780M, but it might not be much faster than the Iris Xe Graphics G7 in older titles. We will perform additional gaming benchmarks over the next couple of days and also take a look at Intel’s XeSS upscaling.
Dota 2 Reborn - 1920x1080 ultra (3/3) best looking | |
NVIDIA GeForce MX550 | |
AMD Radeon 780M | |
Intel Arc 8-Cores iGPU | |
AMD Radeon 780M | |
Intel Iris Xe Graphics G7 96EUs | |
Intel Iris Xe Graphics G7 96EUs | |
AMD Radeon 780M | |
Intel Arc A350M | |
Intel Iris Xe Graphics G7 96EUs |
Final Fantasy XV Benchmark - 1920x1080 High Quality | |
AMD Radeon 780M | |
AMD Radeon 780M | |
Intel Iris Xe Graphics G7 96EUs | |
NVIDIA GeForce MX550 | |
AMD Radeon 780M | |
Intel Arc A350M | |
Intel Iris Xe Graphics G7 96EUs | |
Intel Arc 8-Cores iGPU | |
Intel Iris Xe Graphics G7 96EUs |
We use the game The Witcher 3 for our efficiency test, because the CPU does not have a big impact in this scenario. We can see a big advantage of at least 34 % compared to the old Iris Xe Graphics G7, but the new Arc GPU is not quite on par with the Radeon 780M yet. Apple’s M3 GPUs are still in a completely different league.
Power Consumption / Witcher 3 ultra Efficiency (external Monitor) | |
Apple M3 10-Core GPU | |
Apple M3 Pro 14-Core GPU | |
Apple M3 Pro 18-Core GPU | |
Apple M3 Max 40-Core GPU | |
AMD Radeon 780M | |
AMD Radeon 780M | |
NVIDIA GeForce MX550 | |
Intel Arc 8-Cores iGPU | |
Intel Arc A350M | |
Intel Iris Xe Graphics G7 96EUs | |
Intel Iris Xe Graphics G7 96EUs |
* ... smaller is better
System Performance
We do not see any major improvements in the synthetic benchmarks PCMark 10 as well as the cross-platform benchmark CorssMark.
CrossMark: Overall | Productivity | Creativity | Responsiveness
CrossMark: Overall | Productivity | Creativity | Responsiveness
Performance at lower power limits
Intel often shows the performance at 28 Watts in the marketing material, but the problem is that there will probably not be many Meteor Lake H chips running at such low TDP figures. Even the old Raptor Lake-P models usually ran at much higher power limits and this TDP range is often used by U-series chips, even though they cannot keep up in terms of performance (especially multi-core & GPU).
We still evaluated the multi-core performance of the new Core Ultra 7 155H at fixed power limits of 28 Watts, 35 Watts, and 45 Watts in Cinebench R23. The performance is better compared to Raptor Lake-P (Core i7-1360P) and Raptor Lake-H45 (Core i7-13700H), but the big problem for Intel is AMD’S Ryzen 7 7840U, which offers more performance at all three power levels.
Core Ultra 7 155H | Core i7-1360P | Core i7-13700H | Ryzen 7 7840U | |
---|---|---|---|---|
CB R23 Multi 28 Watts | 10573 points | 9423 points | 9774 points | 12225 points |
CB R23 Multi 35 Watts | 11668 points | 10627 points | 11304 points | 13443 points |
CB R23 Multi 45 Watts | 14073 points | 11759 points | 12990 points | 14432 points |
Efficiency improvements while idling and during light workloads
Intel’s marketing material claims significant power savings while idling and during lighter workloads including Netflix streaming, which is supposed to be handled by the two LowPower efficiency cores of the SoC tile alone, so the compute tile can be turned off. We will try to check these claims over the next couple of days and update this article accordingly. However, we might have to wait a bit until final drivers and software versions are available.
NPU Performance
A Neural Processing Unit can found inside the Intel Core Ultra 7 155H. This part of the processor has the job of processing AI applications particularly efficiently. That means models such as Stable Diffusion or language models can already run on the device. With the UL Procyon AI Interface benchmark we put the GPU head-to-head with the NPU and simultaneously checked the power consumption. In both scenarios, it quickly became clear that the NPU's performance was only slightly below that of the Arc iGPU when it came to processing neural networks but the energy requirements were nearly halved. This definitely makes the AI accelerator more efficient than using the graphics chip for the same applications.
Power consumption UL Procyon Ai interface benchmark on an external monitor
UL Procyon AI Inference for Windows | |
Acer Swift Go 14 SFG14-72 | |
Overall Score Integer NPU |
|
Overall Score Integer GPU |
|
Minisforum Neptune Series HN2673 | |
Overall Score Integer GPU |
|
Acer Predator BiFrost Arc A750 OC | |
Overall Score Integer GPU |
|
Acer Predator BiFrost Arc A770 OC, 16GB GDDR6 | |
Overall Score Integer GPU |
|
Verdict - Meteor Lake lags behind expectations
Our preliminary test results of the new Intel Meteor Lake processor Core Ultra 7 155H are rather sobering, especially in terms of CPU performance. Our results are pretty much in line with the reference scores we got from Intel, so software updates should not really make a big difference here. The overall CPU performance is pretty much the same as it was with Raptor Lake, but the new H-series chips now cover an even wider TDP range (28-115 Watts), so especially the multi-core performance can vary significantly between different laptops.
We are still cautious when it comes to the efficiency and want to wait for final retail samples, before we can give a verdict. Our results so far indicate minor improvements of the efficiency under load, both for single-core as well as multi-core load scenarios. However, Intel is still far behind AMD and Apple, even if the efficiency numbers are still getting a bit better with retail units. At this point, we cannot yet say anything about Intel’s efficiency claims while idling and light workloads, which is also the case for the AI performance.
Intel’s Meteor Lake offers a big boost in GPU performance and can also beat AMD’s Radeon 780M. Both the CPU performance as well as the CPU efficiency under load, however, did not change all that much.
The situation is better for the new Arc GPUs, but you have to keep in mind that they are reserved for the new H-series processors. The performance increase is massive, at least in synthetic benchmarks, and Intel even manages to beat AMD’s Radeon 780M. The situation changes in actual gaming benchmarks though, but we believe driver updates can improve the situation. We will also add more gaming benchmarks of recent titles over the next couple of days and test Intel’s XeSS upscaling. In addition to increased performance, the efficiency of the Arc GPU is also better and it is almost on par with the Radeon 780M.
You might think that the removal of the P-series makes it easier to find a suitable processor, but this is not the case. As mentioned before, the H-series chips now cover an even wider TDP range and customers just don’t know what performance they will get. AMD’s Zen4 processor (4 nm) is still the better choice in the lower TDP range (28 Watts) and the cooling solution does not have to deal with immense short-term power limits. Apple raised the bar even further with the new M3 generation (3 nm), both in terms of performance as well as efficiency.
We are also a bit worried about the Core Ultra U-series chips, which are still equipped with two performance cores. They were hardly mentioned in the press material and the do not get the fast Arc GPU, either, but only a slower version with 4 Xe cores, which might offer the performance of the familiar Iris Xe Graphics G7 (96 EUs).
We will try to update this article with more data as quickly as possible, but it looks like we will have to wait until January before we get our hands on retail devices with Meteor Lake.