Intel Iris Plus Graphics 655 vs NVIDIA GeForce RTX 3050 6GB Laptop GPU vs NVIDIA GeForce RTX 3060 Ti

The Intel Iris Plus Graphics 655 (GT3e) is a processor graphics card announced in September 2017. As the successor to the Intel Iris Graphics 650 (Kaby Lake), the Iris Plus Graphics 655 is used for 28-Watt Coffee Lake-U models. The biggest difference is the doubled eDRAM-cache at 128 MB. There should not be any big changes compared to the Iris Graphics 650.

The so called GT3e version of the Kaby Lake GPU still has 48 Execution Units (EUs), which can reach up to 1200 MHz (previously 1100 MHz) depending on the model. Besides eDRAM cache, the Iris 655 can also access the system memory (2x 64 Bit DDR3L-2133/DDR4-2400) via processor interface.

Compared to the Iris Plus 640 from the 15-Watt models, the Iris 655 only has a slightly higher maximum clock as well as almost twice the TDP, which allows a better utilization of the Turbo Boost potential.

Performance

The exact performance of the Iris Plus Graphics 655 depends on the CPU model, because maximum clock as well as the size of the L3 cache can differ a bit. The system memory (DDR3/DDR4) will influence the performance as well.

The fastest chips are high-clocked Core i7 models like the Core i7-8559U. Depending on the game, the Iris Plus 655 will probably be on par with a dedicated GeForce 930M or GeForce 940MX and can handle smooth gameplay in modern titles in low up to medium settings.

Features

The reworked video engine now fully supports hardware decoding of H.265/HEVC videos. Contrary to Skylake, however, Kaby Lake can now also decode H.265/HEVC Main 10 with a 10-bit color depth as well as Google's VP9 codec. The video output is possible via DP 1.2/eDP 1.3 (up to 3840 x 2160 @60 Hz), whereas HDMI is also supported in the older 1.4a standard. An HDMI 2.0 output can be added via converter from DisplayPort. The GPU can drive up to three displays simultaneously.

Power Consumption

The Iris Plus Graphics 655 is used for 28-Watt processor and therefore small/medium-sized notebooks.

The Nvidia GeForce RTX 3050 6GB Laptop GPU (mobile, GN20-P0-R, 2023 Refresh) is the refresh of the RTX 3050 4GB Laptop GPU (slowest RTX 3000 mobile card) and also based on the GA107 Ampere chip. The 6GB variant offers more CUDA cores (2,560, +25%) but a cut down memory bus to 96 Bit. The clock speed depends on the TGP variant and can range from 713 - 1530 (base) and 1058 - 1740 (boost) for the TGP variants of 35 to 80 Watt (see table below).

The performance is between the old 4GB RTX 3050 and the RTX 3050 Ti and therefore best suited for full HD gaming (1920 x 1080) in medium to high graphic settings. The performance is not sufficient to enable Raytracing in most games, but the Tensor cores can be used for DLSS in some games (and get performance boost with slight quality reduction). Beware, that the low TGP variants will offer a significantly lower performance.

The GA107 chip offers 3,072 FP32 ALUs of which half can also execute INT32 instructions (i.e. 1,536 INT32 ALUs). The RTX 3050 however maybe won't use all ALUs on the chip. With Turing all shaders could still execute FP32 or INT32 instructions. The raytracing and tensor cores on the chip were also improved according to Nvidia. The Ampere chips also include an improved 5th generation video encoder (NVENC for H.264 and H.265) and a 7th generation decoder (for various formats now including AV1).

The GA107 chip is manufactured by Samsung in 8nm (8N), which is not quite able to keep up with the 7nm node at TSMC (e.g. used by AMD and also for the professional GA100 Ampere chip).