When you create a virtual machine (VM) or bare metal instance using
Compute Engine, you specify a machine series and a machine type for the
instance. Each machine series is associated with one or more CPU platforms.
If there are multiple CPU platforms available
for a machine type, you can select a
minimum CPU
platform for
the compute instance.
A CPU platform offers multiple physical processors, and each of these processors
are referred to as a core. For all processors available on
Compute Engine, a single CPU core can run as multiple hardware
multithreads through
Simultaneous multithreading (SMT)
,
which is known on Intel processors as
Intel Hyper-Threading Technology
.
On Compute Engine, each hardware multithread is called a virtual CPU
(vCPU). When vCPUs are reported to the VM as occupying different virtual cores,
Compute Engine ensures that these vCPUs never share the same physical
core.
The
machine type
of your compute instance
specifies its number of vCPUs, and you can infer its number of physical CPU
cores using the default vCPU per core ratio for that machine series:
- For the Tau T2D, Tau T2A, and H3 machine series, VMs always have one vCPU
per core.
- For all other machine series, the compute instances have two vCPUs per core
by default.
You can optionally
set the number of threads per core
,
to a non-default value, which might benefit some workloads. Importantly, when
you do this, the machine type of your compute instance no longer reflects the
correct number of vCPUs. Instead, the
pricing
and number of physical CPU cores remains the same as it would be for the
default two vCPUs per core ratio, and the number of vCPUs is half of the
value indicated by the machine type.
Arm processors
For Arm processors, Compute Engine uses one thread per core. Each vCPU maps
to a physical core with no SMT.
The following table describes the Arm processors that are available for
Compute Engine instances.
CPU processor
|
Processor SKU
|
Supported machine series and types
|
All-core sustained frequency (GHz)
|
Ampere Altra
|
Q64-30
|
|
3.0
|
x86 processors
For most x86 processors, each vCPU is implemented as a single hardware thread.
The Tau T2D machine series is the exception, with one vCPU representing one
physical core.
Intel processors
On Intel Xeon processors,
Intel Hyper-Threading Technology
supports multiple threads running concurrently on each core. The
machine type
of your
compute instance determines the number of its vCPUs and memory.
CPU processor
|
Processor SKU
|
Supported machine series and types
|
Base frequency (GHz)
|
All-core turbo frequency (GHz)
|
Single-core max turbo frequency (GHz)
|
Intel Xeon Scalable Processor
(Emerald Rapids)
5th generation
|
Intel® Xeon® Platinum 8581C Processor
|
|
2.1
|
2.9
|
3.3
|
Intel Xeon Scalable Processor
(Sapphire Rapids)
4th generation
|
Intel® Xeon® Platinum 8490H Processor
|
|
1.9
|
2.9
|
3.5
|
Intel® Xeon® Platinum 8481C Processor
|
|
2.2
|
3.0
|
3.0
|
Intel® Xeon® Platinum 8481C Processor
|
|
2.0
|
3.8
|
2.9
|
Intel Xeon Scalable Processor (Ice Lake)
3rd Generation
|
Intel® Xeon® Platinum
8373C Processor
|
|
2.6
|
3.4
|
3.5
|
Intel Xeon Scalable Processor (Cascade Lake)
2nd Generation
|
Intel® Xeon® Gold 6268CL Processor
|
|
2.8
|
3.4
|
3.9
|
Intel® Xeon® Gold 6253CL Processor
|
|
3.1
|
3.8
|
3.9
|
Intel® Xeon® Platinum 8280L Processor
|
|
2.5
|
3.4
|
4.0
|
Intel® Xeon® Platinum 8273CL Processor
|
|
2.2
|
2.9
|
3.7
|
Intel Xeon Scalable Processor (Skylake)
1st Generation
|
Intel® Xeon® Scalable Platinum 8173M Processor
|
|
2.0
|
2.7
|
3.5
|
Intel Xeon E7 (Broadwell E7)
|
Intel® Xeon® E7-8880V4 Processor
|
|
2.2
|
2.6
|
3.3
|
Intel Xeon E5 v4 (Broadwell E5)
|
Intel® Xeon® E5-2696V4 Processor
|
|
2.2
|
2.8
|
3.7
|
Intel Xeon E5 v3 (Haswell)
|
Intel® Xeon® E5-2696V3 Processor
|
|
2.3
|
2.8
|
3.8
|
Intel Xeon E5 v2 (Ivy Bridge)
|
Intel® Xeon® E5-2696V2 Processor
|
|
2.5
|
3.1
|
3.5
|
Intel Xeon E5 (Sandy Bridge)
|
Intel® Xeon® E5-2689 Processor
|
|
2.6
|
3.2
|
3.6
|
*
N2 machine types that have 96 or more vCPUs require the Intel
Ice Lake CPU.
AMD processors
AMD processors provide optimized performance and scalability using SMT.
In almost all cases, Compute Engine uses two threads per core, and each vCPU
is one thread. Tau T2D is the exception where Compute Engine uses one
thread per core and each vCPU maps to a physical core. The
machine type
of your
compute instance determines the number of its vCPUs and memory.
CPU processor
|
Processor SKU
|
Supported machine series
|
Base frequency (GHz)
|
Effective frequency (GHz)
|
Max boost frequency (GHz)
|
AMD EPYC Genoa
4th Generation
|
AMD EPYC™ 9B14
|
|
2.6
|
3.3
|
3.7
|
AMD EPYC Milan
3rd Generation
|
AMD EPYC™ 7B13
|
|
2.45
|
2.8
|
3.5
|
AMD EPYC Rome
2nd Generation
|
AMD EPYC™ 7B12
|
|
2.25
|
2.7
|
3.3
|
Frequency behavior
The previous tables describe the hardware specifications of the CPUs that are
available with Compute Engine, but keep the following points in mind:
Frequency
: A computer's frequency, or clock speed, which measures the
number of cycles the CPU executes per second, measured in GHz (gigahertz).
Generally, higher frequencies indicate better performance. However, different
CPU designs handle instructions differently, so an older CPU with a higher
clock speed can be outperformed by a newer CPU with a lower clock speed
because the newer architecture deals with instructions more efficiently.
For more information about CPU clock cycles and performance, see
Clock rates and system performance
.
Base frequency
: The frequency at which the CPU runs when the system is
idle or under light load. When running at its base frequency, the CPU draws
less power and produces less heat.
A compute instance's guest environment reflects the base frequency,
regardless of what frequency the CPU is actually running at.
All-core turbo frequency
: The frequency at which each CPU typically
runs when all cores in the socket are not idle at the same time. Different
workloads place different demands on a system's CPU. Boost technologies
address this difference and help processes adapt to the workload demands by
increasing the CPU's frequency.
- Most compute instances get the all-core turbo frequency, even if only
the base frequency is advertised to the guest environment.
- Ampere Altra Arm processors can provide more predictable performance
because the frequency for Arm processors is always the all-core turbo
frequency.
Max turbo frequency
: The frequency a CPU targets when stressed by a
demanding application like a video game or design modeling application. It's
the maximum single-core frequency that a CPU achieves without overclocking.
Processor power management technologies
: Intel processors support multiple
technologies to optimize the power consumption. These technologies are divided
into two categories, or states:
- C-states are states when the CPU has reduced or turned off selected
functions.
- P-states provide a way to scale the frequency and voltage at which the
processor runs so as to reduce the power consumption of the CPU.
Certain C2 (30, 60 vCPUs), C2D (56, 112 vCPUs) and M2 (208, 416 vCPUs)
machine types support instance-provided C-state hints by way of the
MWAIT
instruction.
Compute Engine instances don't provide any facilities for customer
control of P-states.
CPU features
Chip manufacturers add advanced technologies for computations, graphics,
virtualization, and memory management to the CPUs they produce. Google Cloud
supports the use of some of these advanced features with Compute Engine.
Advanced Matrix Extensions (AMX)
Intel AMX
is a new instruction set architecture (ISA) extension designed to accelerate
artificial intelligence (AI) and machine learning (ML) workloads. AMX
introduces new instructions that can be used to perform matrix multiplication
and convolution operations, which are two of the most common operations in AI
and ML.
AMX is supported on Intel Xeon 4th generation processors (code named Sapphire
Rapids) and 5th generation Intel Xeon Scalable processors (code-named Emerald
Rapids), which power the A3, C3, Z3, H3, N4, and X4 machine series. All
machine types in those machine series support AMX instruction sets.
AMX introduces 2-dimensional registers called
tiles
upon which accelerators
can perform operations. AMX is intended as an extensible architecture. The first
accelerator implemented is called tile matrix multiply unit (TMUL). Each
CPU core of the Sapphire Rapids processor has an independent AMX TMUL unit.
More technical details about Intel AMX can be found at
Intel AMX support in 5.16
.
Intel offers a tutorial on AMX at
Code Sample: Intel® Advanced Matrix Extensions (Intel® AMX) - Intrinsics Functions
.
Requirements for using AMX
Intel AMX instructions have certain minimum software requirements such as:
- For custom images, AMX is supported with Linux kernel version 5.16 or
later.
- Compute Engine offers support for AMX in the following
public images
:
- CentOS Stream 8 or later
- Container-Optimized OS 109 LTS or later
- RHEL 8 (latest build) or later
- Rocky Linux 8 (latest build) or later
- Ubuntu 22.04 or later
- Windows Server 2022 or later
- Tensorflow
2.9.1 or greater
- Intel extension for
Intel® Optimization for PyTorch
For regional availability of the machine series that support AMX, see
Available regions and zones
and filter
the table to show only the Sapphire Rapids or Emerald Rapids CPUs.
CPU features available to bare metal instances
In addition to offering all the raw compute resources of the server, bare metal
instances that run on 4th generation Intel Xeon Scalable Processors can use
several on board, function-specific accelerators and offloads:
- Intel-QAT
: Intel QuickAssist Technology (Intel QAT) accelerates
compression, encryption, and decryption
- Intel-DLB
: Intel Dynamic Load Balancer (Intel DLB) helps to speed up
data queues
- Intel IAA
: Intel In-Memory Analytics Accelerator (Intel IAA) improves
query processing performance.
- Intel DSA
: Intel Data Streaming Accelerator (Intel DSA) helps to
copy and move data faster.
Confidential Computing
To protect your data while it's in use, CPU platforms that support
Confidential Computing technologies can be used to create
Confidential VM
instances.
To learn more about the requirements for creating a Confidential VM
instance, see
Supported configurations
.
What's next
Try it for yourself
If you're new to Google Cloud, create an account to evaluate how
Compute Engine performs in real-world
scenarios. New customers also get $300 in free credits to run, test, and
deploy workloads.
Try Compute Engine free