The Intel Xe GPU found on the 11th generation Tiger Lake CPUs has been re-tested and this time the chip performs on par with the discrete graphics of the faster NVIDIA MX series found in most mainstream laptops.
Intel Tiger Lake Xe GPU with 96 EU games Discrete NVIDIA GeForce MX350 GPU and fires outperform AMD’s Vega 7nm iGPU in latest benchmarks
The Xe GPU specifies that it has been tested as part of the Core i7-1165G7 configuration. Please note that the Core i7-1165G7 is not the fastest Tiger Lake CPU configuration as that title belongs to the Core i7-1185G7. Regardless, the Xe GPU is based on the Gen 12 GPU architecture which features 96 UEs that make up 768 cores in total. This chip has a 1.3 GHz clock and the chip shares its power with the entire Tiger Lake SOC which has a basic TDP of 15W which is configurable up to 28W. The Xe GPU has been tested with LPDD4x memory that operates at 4266 MHz.
Intel Tiger Lake vs AMD Renoir Mobility CPU comparison:
|Name of the CPU family||Intel Tiger Lake-U||AMD Renoir U Series.|
|Family brand||Intel 11th Gen Core (U series)||AMD Ryzen 4000 (U series)|
|CPU core architecture||Willow Cove||Zen 2|
|CPU core / thread (max)||4/8||8/16|
|Max CPU Clocks||TBD (Core i7-1185G7)||4.2 GHz (Ryzen 7 4800U)|
|GPU basic architecture||Xe graphics engine||Vega Enhanced 7nm|
|Maximum number of GPU cores||96 EU (768 cores)||8 CU (512 cores)|
|Max GPU Clocks||TBD||1750 MHz|
|TDP (cTDP Down / Up)||15 W (12 W-28 W)||15 W (10 W-25 W)|
|To launch||Mid 2020||March 2020|
Intel Tiger Lake Xe GPU vs NVIDIA Pascal GeForce MX350 Graphics Performance:
The first reference comparison is between the Intel Xe GPU with 96 EU (768 cores) and the NVIDIA GeForce MX350 with 5 SM (640 cores). NVIDIA MX350 not only features a higher graphics frequency of 1.47 GHz, but is also equipped with 2 GB of GDDR5 memory which offers greater bandwidth specifically to the GPU itself.
In Geekbench 4’s OpenCL benchmark, the Tiger Lake Xe GPU scores 59845 points while NVIDIA’s GeForce MX350 scores 59828 points. There’s no difference in performance, but for Intel’s Xe GPU, this is a huge feat considering it offers the same performance as a discrete-level GPU while still being limited in terms of bandwidth and power.
The interesting thing is how each test shows different results between the two GPUs tested. From Intel, they do really well in most of the sub-tests, especially the Gaussian Blue benchmark, but NVIDIA manages a huge advantage in the particle physics test which compensates for the overall gains achieved by Intel’s Xe chip.
Also, what’s interesting is that a leaked rumor from Apple’s Bionic A12Z GPU appeared in the Geekbench 5 database just a few days ago and was spotted by Rogame. The Apple GPU that will be incorporated into its Macbook line is slightly slower than GeForce MX350. The MX350 marks 13520 while the Bionic A12Z AicZ GPU marks 11315. This is approximately a 20% advantage for the NVIDIA GPU. The Pascal MX350 configuration used here is the low-end SKU that operates at 15 W and has a clock speed of 936 MHz compared to 1.47 GHz of the 25 W variant. The A12Z has 8 CU and 1 GHz clocks.
I know GB4 and GB5 are very different benchmarks, but if Intel’s Xe GPU also scales in GB5 tests compared to the MX350 in GB4, Intel will also have a comfortable advantage over Apple’s Bionic GPU.
Intel Tiger Lake Xe 96 EU vs Tiger Lake Xe 80 EU graphics performance:
The benchmarks also compare Intel Tiger Lake Xe 96 EU (Core i7-1165G7) with the 80 EU configuration (Core i5-1135G7). The Core i5-1135G7 is a lower clocked SKU when it comes to CPU and also features a slightly attenuated Xe GPU. The 80 UEs represent 640 cores that correspond to the GeForce MX350 but still at 1.30 GHz (compared to 1.47 GHz on the GeForce MX350).
Here we can see that the GPU score drops by about 13.5% compared to the Core i7-1165G7 which is expected due to the 16.7% lower core. There are no secondary test anomalies as in the case of the MX350 benchmarks since both Xe GPUs share the same Gen 12 GPU architecture while the NVIDIA Pascal architecture may work better in some segments.
Intel Tiger Lake Xe vs AMD Ryzen 4000 ‘Renoir’ 7nm Vega iGPU GPU:
Compared to faster AMD Ryzen 4000 Renoir U series SKUs, the Ryzen 7 4800U featuring the 1.75 GHz Vega 8 (512 cores) iGPU, the Tiger Lake Xe GPU with 96 EU (768 cores) at 1.3 GHz just around 30% lead is impressive and similar to the gains we saw earlier in 3DMark losses. The Vega GPU has 30% lower cores but also offers a 35% GPU frequency advantage over Intel’s iGPU.
The same is true when comparing the Core i5-1135G7 (GPU Xe with 80 EU or 640 cores at 1.3 GHz) with AMD Ryzen 5 4600U (Vega 6 with 384 cores at 1.5 GHz). The Intel Tiger Lake CPU marks an advantage of around 35% in the same benchmark which is very impressive. Below is a table showing all the reference parameters and how they overlap.
Geekbench 4 OpenCL GPU performance comparisons:
|GPU name||GPU architecture||Core GPU||GPU clock||Point|
|Intel Xe G7||GPU 10nm Gen 12||768 cores||1.30 GHz||59845|
|NVIDIA GeForce MX350||GPU Pascal 14nm||640 cores||1.47 GHz||59828|
|Intel Xe G7||GPU 10nm Gen 12||640 cores||1.30 GHz||51741|
|AMD Vega 8||GPU Vega 7nm||512 cores||1.75 GHz||46620|
|AMD Vega 6||GPU Vega 7nm||384 cores||1.50 GHz||38787|
Intel Tiger Lake processors are expected to arrive in a few months and will present some new changes to the architecture. First, they will have the new Willow Cove cores that will replace the Sunny Cove cores that are currently present on Ice Lake processors. Together with the new cores, we will get cache redesigns as indicated above, new transistor optimizations and advanced security features. Intel will also present its Xe-LP GPUs on Tiger Lake chips that would offer a double perf increase compared to the Gen 11 GPUs currently on Ice Lake chips.
We have already seen an impressive demonstration of the first Tiger Lake champions running Battlefield V on a portable laptop, offering an average of 30 FPS at 1080p resolution at high settings.
This and in combination with the Xe GPU architecture, the 10nm + node should also provide increased clocks compared to the first iteration of the 10nm + architecture present on the Ice Lake chips. Intel Tiger Lake 10nm CPUs are expected to be present in a wide range of next generation notebooks and laptops this summer. Intel has already launched its promotional campaign for the new 11th generation notebook family and you can certainly expect a launch that will come soon!