The Intel Celeron N2820 is a power efficient dual-core SoC for entry-level notebooks. It is clocked at up to 2.4 GHz and part of the Bay Trail-M platform. Thanks to the specially optimized 22 nanometer low-power process (P1271) with tri-gate transistors, performance and energy efficiency have been significantly improved compared to previous Intel Atom CPUs.
Architecture
The processor cores are based on the new Silvermont architecture, which is an out-of-order design for the first time. The increased utilization of the pipeline and many other improvements (optimized branch prediction, increased buffers, enhanced decoders) have increased the performance per clock by about 50 percent. At the same time, however, the Hyper-Threading feature of the previous generation has been removed. Other major changes are the support for new instruction set extensions such as SSE 4.1 and 4.2 as well as AES-NI (depending on the model).
Performance
Thanks to the improved performance per clock, the Celeron N2820 is faster than previous Intel Atoms, e.g. the N2850. Therefore, the N2820 even competes with entry-level AMD APUs like the AMD E1-2500. For simple everyday tasks such as Internet or Office the performance is adequate, but not for complex software or modern games.
Graphics
The graphics unit of Bay Trail is based on the Intel Gen7 architecture, which supports DirectX 11 and is also found in the Ivy Bridge series (e.g. HD Graphics 4000). With only 4 EUs (Execution Units) and a relatively low clock speed of up to 756 MHz, the GPU is even slower than the HD Graphics (Ivy Bridge). Therefore, only older and less demanding games will run fluently.
Power Consumption
The entire SoC is rated at a TDP of 7.5 watts. Thus, the chip can be used in compact subnotebooks.
The Intel Celeron N2806 is a power efficient dual-core SoC for entry-level notebooks. It is clocked at 1.6 - 2.0 GHz and part of the Bay Trail-M platform. Thanks to the specially optimized 22 nanometer low-power process (P1271) with tri-gate transistors, performance and energy efficiency have been significantly improved compared to previous Intel Atom CPUs.
Architecture
The processor cores are based on the new Silvermont architecture, which is an out-of-order design for the first time. The increased utilization of the pipeline and many other improvements (optimized branch prediction, increased buffers, enhanced decoders) have increased the performance per clock by about 50 percent. At the same time, however, the Hyper-Threading feature of the previous generation has been removed. Other major changes are the support for new instruction set extensions such as SSE 4.1 and 4.2 as well as AES-NI (depending on the model).
Performance
Thanks to the improved performance per clock, the Celeron N2806 is faster than previous Intel Atoms, e.g. the N2800. Therefore, the N2806 competes with entry-level AMD APUs like the AMD E1-1200. For simple everyday tasks such as Internet or Office the performance is adequate, but not for more complex software or modern games.
Graphics
The graphics unit of Bay Trail is based on the Intel Gen7 architecture, which supports DirectX 11 and is also found in the Ivy Bridge series (e.g. HD Graphics 4000). With only 4 EUs (Execution Units) and a relatively low clock speed of 313 - 756 MHz, the GPU is even slower than the HD Graphics (Ivy Bridge). Therefore, only older and less demanding games will run fluently.
Power Consumption
The entire SoC is rated at a TDP of 4.5 watts (2.5 W SDP). Thus, the chip can be used in passively cooled subnotebooks.
- Range of benchmark values for this graphics card - Average benchmark values for this graphics card * Smaller numbers mean a higher performance 1 This benchmark is not used for the average calculation
v1.28
log 11. 22:44:02
#0 ran 0s before starting gpusingle class +0s ... 0s
#1 checking url part for id 4991 +0s ... 0s
#2 checking url part for id 4987 +0s ... 0s
#3 redirected to Ajax server, took 1728679442s time from redirect:0 +0s ... 0s
#4 did not recreate cache, as it is less than 5 days old! Created at Thu, 10 Oct 2024 05:17:16 +0200 +0s ... 0s
#5 composed specs +0.006s ... 0.006s
#6 did output specs +0s ... 0.006s
#7 getting avg benchmarks for device 4991 +0.003s ... 0.009s
#8 got single benchmarks 4991 +0.006s ... 0.015s
#9 getting avg benchmarks for device 4987 +0.001s ... 0.016s
#10 got single benchmarks 4987 +0.003s ... 0.018s
#11 got avg benchmarks for devices +0s ... 0.018s
#12 min, max, avg, median took s +0.024s ... 0.042s