Intel Celeron 3965U vs Intel Core i7-1270P vs Intel Core i7-7920HQ

Intel Celeron 3965U

The Intel Celeron 3965U is an ULV (ultra low voltage) dual-core SoC based on the Kaby-Lake architecture and has been launched in the first quarter of 2017. The CPU can be found in ultrabooks as well as normal notebooks. In addition to two CPU cores without Hyper-Threading clocked at 2.2 GHz (no Turbo Boost), the chip also integrates an HD Graphics 610 GPU and a dual-channel DDR4-2133/DDR3L-1600 memory controller. The SoC is manufactured using a 14 nm process with FinFET transistors.

Architecture

Intel basically uses the same micro architecture compared to Skylake, so the per-MHz performance does not differ. The manufacturer only reworked the Speed Shift technology for faster dynamic adjustments of voltages and clocks, and the improved 14nm process allows much higher frequencies combined with better efficiency than before.

Performance

Due to the missing Turbo Boost and the low clock speeds, especially the single thread performance is very limited which results in a lower performance even for lower demanding tasks. The performance should be between the Intel Pentium 4405U and 4415U. Still, the CPU has sufficient power for office and multimedia purposes.

Graphics

The integrated graphics unit called HD Graphics 610 (similar to the HD Graphics 510) represents the "GT1" version of the Kaby Lake GPU (Intel Gen. 9). Its 12 Execution Units, also called EUs, are clocked at 300 - 900 MHz and offer a performance somewhat below the older HD Graphics 4400. Only a few games of 2015 can be played smoothly in lowest settings.

Power Consumption

Specified at a TDP of 15 W (including CPU, GPU and memory controller), the CPU is best suited for small notebooks and ultrabooks (11-inches and above). Optionally, the TDP can be lowered to 10 watts (cTDP down), reducing both heat dissipation and performance and allowing even more compact designs.

Intel Core i7-1270P

The Intel Core i7-1270P is a higher-end Alder Lake-P family CPU, an expensive 28 W part meant for use in ultra-light, ultra-thin (yet actively cooled) laptops. This CPU was announced in early 2022 and it has 4 performance cores as opposed to the 6 cores of the top-of-the-line 1280P (P-cores, Golden Cove architecture) mated to 8 efficient cores (E-cores, Gracemont architecture). The P-cores are Hyper-Threading-enabled for a total of 16 threads when combined with the E-cores. The clock speeds range from 2.2 GHz to 4.8 GHz for the performance cluster and 1.6 GHz to 3.5 GHz for the efficient cluster. Full vPro feature set is supported by this Core i7 ("Enterprise" tier, allowing for remote device management). Its shortcomings as compared with the mighty i7-1280P include the smaller L3 cache, lower core count, lower clock speeds; the performance is slated to be significantly lower as a result.

A brief look at the specifications instantly reveals this i7 series chip to be very similar to the Core i5-12600H, a more power-hungry processor targeted at gaming laptops.

Architecture

The i7 is a continuation of Intel's efforts to use the ARM-developed big.LITTLE technology for its own benefit. A single "little" Alder Lake core is supposed to be as fast as a Skylake core (as found in the venerable Core i7-6700HQ among other options) which is six years old at this point. All of an Intel Core i7-1270P's CPU cores enjoy access to 18 MB of L3 cache. The integrated memory controller supports various memory types up to LPDDR5-5200, DDR5-4800, LPDDR4x-4267 or DDR4-3200. Intel suggests using no more than 64 GB, for reference. Just like the other 12th Gen Intel Core processors, Core i7-1270P comes with Thread Director which is a new functionality designed to help Windows 11 decide which cores to use for what workload for best performance and efficiency possible. Hardware acceleration of AI algorithms is supported via GNA 3.0 and DL Boost (via AVX2). PCI-Express 5.0 support has not found its way into Alder Lake P processors, so users will have to be content with PCI-Express 4.0 for the time being. Four PCI-Express 4 lanes allow for a read/write rate of up to 7.9 GB/s, provided a suitably fast NVMe SSD is used.

Please note this is not a user-replaceable CPU. It gets soldered permanently on to the motherboard (BGA1744 socket interface).

Performance

The 12 CPU cores are not just able to outshine any outgoing quad-core Tiger Lake part, the i7-1195G7 included. The average 1270P in our database directly competes with the Ryzen 7 5825U, the Ryzen 7 7730U and the Ryzen 7 7735U, meaning this little Core i7 is fast enough to make most consumers happy as of mid 2023.

The fairly high processing power comes at a cost. A single Golden Cove core can consume more than 20 W when under heavy load. Your mileage may thus vary depending on how high the Power Limits are and how competent the cooling solution of your laptop is.

Graphics

The built-in graphics adapter in the form of the 96 EU Iris Xe running at up to 1.40 GHz has seen no change from what was built into the 11th Gen Tiger Lake-UP3 processors, like an i7-1165G7, which is hardly a downside as this iGPU is loaded with modern features such as AV1 video decoding capability and SUHD 4320p monitor support. Up to 4 monitors can be used simultaneously with this iGPU. We expect the gaming performance to be reasonably close to that of NVIDIA's MX350.

In other words, the Xe is good enough for most games at 1080p resolution / Medium settings, provided the Power Limits are high enough and the cooling solution is competent enough. Fast RAM is a prerequisite for decent performance as well (the Xe has to make do with no dedicated video memory).

Last but not the least, we discovered that the GPU utilization when playing YouTube UHD 2160p60 videos is higher than it was with Tiger Lake chips.

Power consumption

The i7's base power consumption (also known as the default TDP or Power Limit 1) is 28 W, with 64 W being its maximum Turbo power consumption (also known as the PL2). As for the "Minimum Assured" power consumption, Intel's guidelines mention 20 W. All in all, an active cooling solution is a must for such a chip.

The CPU is built with Intel's fourth-gen 10 nm process marketed as Intel 7 for decent, as of late 2022, energy efficiency. It's still a rather power-hungry CPU; a single P-core will happily consume more than 20 W when under heavy load. A couple of the higher-end 7 nm U-class AMD Ryzen 5000 chips are not nearly as power-hungry while delivering similar or higher performance levels.

Intel Core i7-7920HQ

The Intel Core i7-7920HQ is a fast quad-core processor for notebooks based on the Kaby Lake architecture and was announced in January 2017. It is the top model of the consumer series at the time of the announcement. Only the Xeon E3-1535M v6 is faster (100 - 200 MHz higher Turbo clocks). Besides four cores including Hyper-Threading support running at 3.1-4.1 GHz (4 cores up to 3.7 GHz, 2 cores up to 3.9 GHz), the processor is also equipped with the HD Graphics 630 GPU as well as a dual-channel memory controller (DDR3L-1600/DDR4-2400). It is manufactured in a 14nm process with FinFET transistors.

Architecture

Intel basically uses the same micro architecture compared to Skylake, so the per-MHz performance does not differ. The manufacturer only reworked the Speed Shift technology for faster dynamic adjustments of voltages and clocks, and the improved 14nm process allows much higher frequencies combined with better efficiency than before.

Performance

The performance is a bit higher compared to the Skylake predecessor Core i7-6920HQ (2.9-3.8 GHz) thanks to slightly higher clocks (up to 7.9%), so it is the fastest mobile consumer processor in the beginning of 2017 (mobile Xeon E5-1535M v6 has even higher Turbo clocks). The performance is sufficient even for very demanding tasks and on par with powerful desktop quad-core processors.

Graphics

The integrated Intel HD Graphics 630 has 24 Execution Units (similar to previous HD Graphics 530) running at 350 - 1100 MHz. The performance depends a lot on the memory configuration; it should be comparable to a dedicated Nvidia GeForce 920M in combination with fast DDR4-2133 dual-channel memory.

Contrary to Skylake, Kaby Lake now supports hardware decoding for H.265/HEVC Main 10 with a 10-bit color depth as well as Google's VP9 codec. The dual-core Kaby Lake processors, which were announced in January, should also support HDCP 2.2.

Power Consumption

The chip is manufactured in an improved 14nm process with FinFET transistors, which improves the efficiency even further. Intel still specifies the TDP with 45 Watts, but it can also be reduced to 35 Watts by the notebook manufacturers (cTDP down). This will obviously affect the performance, because the Turbo Boost cannot be maintained for longer periods.