Google Tensor G2 | AMD EPYC 7F72 | |
CPU comparisonGoogle Tensor G2 or AMD EPYC 7F72 - which processor is faster? In this comparison we look at the differences and analyze which of these two CPUs is better. We compare the technical data and benchmark results.
The Google Tensor G2 has 8 cores with 8 threads and clocks with a maximum frequency of 2.85 GHz. Up to 12 GB of memory is supported in 2 memory channels. The Google Tensor G2 was released in Q4/2022. The AMD EPYC 7F72 has 24 cores with 48 threads and clocks with a maximum frequency of 3.70 GHz. The CPU supports up to GB of memory in 8 memory channels. The AMD EPYC 7F72 was released in Q2/2020. |
||
Google Tensor (3) | Family | AMD EPYC (129) |
Google Tensor G2 (1) | CPU group | AMD EPYC 7002 (24) |
2 | Generation | 2 |
G2 | Architecture | Rome (Zen 2) |
Mobile | Segment | Desktop / Server |
Google Tensor | Predecessor | -- |
-- | Successor | -- |
|
||
CPU Cores and Base FrequencyThe Google Tensor G2 has 8 CPU cores and can calculate 8 threads in parallel. The clock frequency of the Google Tensor G2 is 2.85 GHz while the AMD EPYC 7F72 has 24 CPU cores and 48 threads can calculate simultaneously. The clock frequency of the AMD EPYC 7F72 is at 3.20 GHz (3.70 GHz). |
||
Google Tensor G2 | Characteristic | AMD EPYC 7F72 |
8 | Cores | 24 |
8 | Threads | 48 |
hybrid (Prime / big.LITTLE) | Core architecture | normal |
No | Hyperthreading | Yes |
No | Overclocking ? | No |
2.85 GHz 2x Cortex-X1 |
A-Core | 3.20 GHz (3.70 GHz) |
2.35 GHz 2x Cortex-A78 |
B-Core | -- |
1.80 GHz 4x Cortex-A55 |
C-Core | -- |
NPU AI performanceThe performance values of the processor's AI unit. The isolated NPU performance is specified here, the total AI performance (NPU+CPU+iGPU) can be higher. Processors with support for artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. |
||
Google Tensor G2 | Characteristic | AMD EPYC 7F72 |
Google Tensor AI | AI hardware | -- |
Google Edge TPU @ 4 TOPS | AI specifications | -- |
-- | NPU + CPU + iGPU | -- |
Integrated graphics (iGPU)The Google Tensor G2 or AMD EPYC 7F72 has integrated graphics, called iGPU for short. The iGPU uses the system's main memory as graphics memory and sits on the processor's die. |
||
ARM Mali-G710 MP7 | GPU | no iGPU |
0.90 GHz | GPU frequency | -- |
-- | GPU (Turbo) | -- |
Vallhall 3 | GPU Generation | -- |
4 nm | Technology | |
1 | Max. displays | |
7 | Compute units | -- |
-- | Shader | -- |
No | Hardware Raytracing | No |
No | Frame Generation | No |
-- | Max. GPU Memory | -- |
12 | DirectX Version | -- |
Hardware codec supportA photo or video codec that is accelerated in hardware can greatly accelerate the working speed of a processor and extend the battery life of notebooks or smartphones when playing videos. |
||
ARM Mali-G710 MP7 | GPU | no iGPU |
Decode / Encode | Codec h265 / HEVC (8 bit) | No |
Decode / Encode | Codec h265 / HEVC (10 bit) | No |
Decode / Encode | Codec h264 | No |
Decode / Encode | Codec VP9 | No |
Decode / Encode | Codec VP8 | No |
Decode | Codec AV1 | No |
Decode / Encode | Codec AVC | No |
Decode / Encode | Codec VC-1 | No |
Decode / Encode | Codec JPEG | No |
Memory & PCIeThe Google Tensor G2 can use up to 12 GB of memory in 2 memory channels. The maximum memory bandwidth is 53.0 GB/s. The AMD EPYC 7F72 supports up to GB of memory in 8 memory channels and achieves a memory bandwidth of up to 51.2 GB/s. |
||
Google Tensor G2 | Characteristic | AMD EPYC 7F72 |
LPDDR5-5500 | Memory | DDR4-3200 |
12 GB | Max. Memory | |
2 (Dual Channel) | Memory channels | 8 (Octa Channel) |
53.0 GB/s | Max. Bandwidth | 51.2 GB/s |
No | ECC | Yes |
8.00 MB | L2 Cache | -- |
4.00 MB | L3 Cache | 192.00 MB |
-- | PCIe version | 4.0 |
-- | PCIe lanes | 128 |
-- | PCIe Bandwidth | 252.0 GB/s |
Thermal ManagementThe thermal design power (TDP for short) of the Google Tensor G2 is 10 W, while the AMD EPYC 7F72 has a TDP of 240 W. The TDP specifies the necessary cooling solution that is required to cool the processor sufficiently. |
||
Google Tensor G2 | Characteristic | AMD EPYC 7F72 |
10 W | TDP (PL1 / PBP) | 240 W |
-- | TDP (PL2) | -- |
-- | TDP up | -- |
-- | TDP down | -- |
-- | Tjunction max. | -- |
Technical detailsThe Google Tensor G2 is manufactured in 4 nm and has 12.00 MB cache. The AMD EPYC 7F72 is manufactured in 7 nm and has a 192.00 MB cache. |
||
Google Tensor G2 | Characteristic | AMD EPYC 7F72 |
4 nm | Technology | 7 nm |
Chiplet | Chip design | Chiplet |
Armv8-A (64 bit) | Instruction set (ISA) | x86-64 (64 bit) |
-- | ISA extensions | SSE4a, SSE4.1, SSE4.2, AVX2, FMA3 |
-- | Socket | SP3 |
None | Virtualization | AMD-V, SVM |
No | AES-NI | Yes |
Android | Operating systems | Windows 10, Linux |
Q4/2022 | Release date | Q2/2020 |
-- | Release price | 2450 $ |
show more data | show more data | |
Google Tensor G2
8C 8T @ 2.85 GHz |
|||
AMD EPYC 7F72
24C 48T @ 3.70 GHz |
Google Tensor G2
8C 8T @ 2.85 GHz |
|||
AMD EPYC 7F72
24C 48T @ 3.50 GHz |
Google Tensor G2
8C 8T @ 2.85 GHz |
|||
AMD EPYC 7F72
24C 48T @ 3.70 GHz |
Google Tensor G2
8C 8T @ 2.85 GHz |
|||
AMD EPYC 7F72
24C 48T @ 3.50 GHz |
Google Tensor G2
8C 8T @ 2.85 GHz |
|||
AMD EPYC 7F72
24C 48T @ 3.70 GHz |
Google Tensor G2
ARM Mali-G710 MP7 @ 0.90 GHz |
|||
AMD EPYC 7F72
@ 0.00 GHz |
Google Tensor G2
8C 8T @ 2.85 GHz |
|||
AMD EPYC 7F72
24C 48T @ 3.20 GHz |
Google Tensor G2
8C 8T @ 2.85 GHz |
|||
AMD EPYC 7F72
24C 48T @ 3.20 GHz |
Devices using this processor |
|
Google Tensor G2 | AMD EPYC 7F72 |
Google Pixel 7 Google Pixel 7 Pro |
Unknown |