Intel Arc A310 vs Intel Iris Plus Graphics 650 vs Intel HD Graphics 630

Intel Arc A310

The Intel Arc A310 is a dedicated entry-level graphics card from Intel for desktops. It is based on the ACM-G11 chip and offers 6 of the 8 Xe cores (96 ALUs), 6 of the 8 ray tracing units, 1.152 MB L1 cache and 4MB L2 cache. The memory interface is 64 bits wide and supports 4GB GDDR6 graphics memory with 15.5 Gbps. The TGP is between 40 and 75 watts depending on the model.

The A310 is similar to the mobile Arc A350Mexcept for the higher clock rates of the cores and memory.

The ACM-G11 chip is manufactured at TSMC in 6nm (N6 process) and offers 7.2 billion transistors and is 157 mm2 in size. It integrates two media engines for VP9, AVC, HEVC, AV1 8k60 12-bit HDR decoding and 8k 10-bit HDR encoding. The integrated 4 display pipes support 4x 4k120 HDR, HDMI 2.0B, DP 2.0 10G and Adaptive Sync.

Intel Iris Plus Graphics 650

The Intel Iris Plus Graphics 650 (GT3e) is a processor graphics card for Kaby Lake models announced in January 2017. As the successor to the Intel Iris Graphics 550 (Skylake), the Iris Plus Graphics 650 is used for 28-Watt models and is equipped with 64 MB eDRAM cache. There should not be any big changes compared to the Iris Graphics 550.

The so called GT3e version of the Kaby Lake GPU probably still has 48 Execution Units (EUs), which can reach up to 1100 MHz depending on the model. Besides eDRAM cache, the Iris 650 can also access the system memory (2x 64 Bit DDR3L-1600/DDR4-2400) via processor interface.

Compared to the Iris Plus 640 from the 15-Watt models, the Iris 650 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 650 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 i7-7567U. Depending on the game, the Iris Plus 650 will probably be on par with a dedicated GeForce 930M 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 650 is used for 28-Watt processor and therefore medium-sized notebooks.

Intel HD Graphics 630

The Intel HD Graphics 630 (GT2) is an integrated graphics card, which can be found in various desktop and notebook processors of the Kaby-Lake generation (Kaby-Lake-H quad-core chip). The "GT2" version of the GPU offers 24 Execution Units (EUs) and the clocks depend on the CPU model. Due to its lack of dedicated graphics memory or eDRAM cache, the HD 630 has to access the main memory (2x 64-bit DDR3L-1600 / DDR4-2133).

Performance

The exact performance of the HD Graphics 630 depends on various factors like TDP, L3 Cache, memory (DDR3/DDR4) and maximum clock rate of the specific model. However, it should be fairly similar to the HD Graphics 530 (see for gaming benchmarks) and therefore only suited for low demanding games like Overwatch or Farming Simulator 2017 (low details).

Features

The revised video engine in the Kaby Lake chips now supports H.265/HEVC Main10 profile at 10-bit color depth and also the VP9 codec in hardware. Furthermore, HDCP 2.2 is also supported in all chips, which allows Netflix 4K videos, for instance. HDMI 2.0 however is still only supported with an external converter chip (LSPCon).

Power Consumption

The HD Graphics 630 can be found in several notebook and desktop processors of different TDP classes (35 - 91 W). Thanks to the improved 14nm+ process, the power consumption could be slightly lower compared to Skylake CPUs.