AWS puts its latest homebrew Arm CPU – the Graviton3 – into production
(2022/05/24)
- Reference: 1653371469
- News link: https://www.theregister.co.uk/2022/05/24/aws_puts_graviton3_arm_cpus/
- Source link:
Amazon Web Services has made its latest homebrew CPU, the Graviton3, available to rent in its Elastic Compute Cloud (EC2) infrastructure-as-a-service offering.
The cloud colossus [1]launched Graviton3 at its late 2021 re:Invent conference, revealing that the 55-billion-transistor device includes 64 cores, runs at 2.6GHz clock speed, can address DDR5 RAM and 300GB/sec max memory bandwidth, and employs 256-bit Scalable Vector Extensions.
The chips were offered as a tech preview to select customers. And on Monday, AWS made them available to all comers in a single instance type named C7g.
[2]
EC2's C-series instances are billed as ideal for compute intensive tasks. The series is now in its seventh generation – and the only seventh-gen instance uses Graviton3. Intel Xeons and AMD EPYCs are currently confined to sixth-gen instance types.
[3]
[4]
Take that , you x86 dinosaurs.
[5]A peek into Gigabyte's GPU Arm for AI, HPC shops
[6]AMD reveals 5nm Ryzen 7000 powered by Zen 4 cores
[7]The 'substantial contributions' Intel has promised to boost RISC-V adoption
[8]Intel's Habana unit reveals new Nvidia A100 challengers
The C7g instances offer eight sizes, with 1, 2, 4, 8, 16, 32, 48, and 64 vCPUs.
The Register has looked up hourly prices for the C7 instance, the C6 instance that uses the Graviton 2, and the C-series instances running the third-gen Xeon and EPYC processors. We used the US West (Oregon) region as our guide, as it is one of just two regions currently offering the Graviton3. Our research considered instances running the same number of vCPUs offered by the C7 instance type.
As the table below shows, Graviton3 instances cost more than Graviton2-powered rent-a-servers, but less than their x86 competitors. AWS offers other ways to consume its infrastructure at lower prices.
vCPUs
C7g Graviton3
C6i 3rd-gen Xeon
C6a 3rd-gen EPYC
C6g Graviton2
1
$0.036
N/A
N/A
$0.034
2
$0.073
$0.085
$0.077
$0.068
4
$0.145
$0.170
$0.153
$0.136
8
$0.290
$0.340
$0.306
$0.272
16
$0.580
$0.680
$0.612
$0.544
32
$1.160
$1.360
$1.224
$1.088
48
$1.740
$2.040
$1.836
$1.632
64
$2.320
$2.720
$2.448
$2.176
The AWS [9]announcement of Graviton3 going into production mentions that Snap Inc., operator of Snapchat and Bitmoji, plans to adopt the new silicon because it has proven faster than Graviton2. That is not great news for Google Cloud, as Snap signed a five-year, $2 billion deal with the ad giant in 2017. Five years later we discover that the social network operator has gone multi-cloud!
AWS's post announcing the C7 instances points out that migrating to Gravitons from x86 isn't hard for many workloads – especially if those workloads are AWS services like its own container and database services.
[10]
Which is utterly self-serving, but also an indicator that, as AWS brings more of its own services to its own silicon, trying Graviton silicon will become less onerous.
The timing of AWS's Graviton3 announcement appears not to have been co-incidental, as it came a few hours before Nvidia revealed [11]server designs based on its own high-end processors .
Perhaps AWS hoped to steal some of Nvidia's thunder.
[12]
Yet the combined effect of the two announcements may be more significant. Together they demonstrate that enterprise computing buyers can now consider multiple mature, well-backed technology choices beyond the x86 architecture. And there is more to come as Microsoft, Oracle, and others introduce their own Arm-powered servers, not t mention the imminent arrival of [13]SmartNICs as accessible on-prem technology. ®
Get our [14]Tech Resources
[1] https://www.theregister.com/2021/12/01/aws_reinvent_graviton_3/
[2] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=2&c=2YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0
[3] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0
[4] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0
[5] https://www.theregister.com/2022/05/23/gigabyte_intros_arm_server/
[6] https://www.theregister.com/2022/05/23/amd_zen4_am5_mendocino_computex/
[7] https://www.theregister.com/2022/05/17/intel_riscv_contributions/
[8] https://www.theregister.com/2022/05/10/intels_habana_unit_reveals_new/
[9] https://aws.amazon.com/blogs/aws/new-amazon-ec2-c7g-instances-powered-by-aws-graviton3-processors/
[10] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0
[11] https://www.theregister.com/2022/05/24/nvidia_cpu_hpc/
[12] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0
[13] https://www.theregister.com/2022/05/20/smartnic_cloud_datacenter/
[14] https://whitepapers.theregister.com/
The cloud colossus [1]launched Graviton3 at its late 2021 re:Invent conference, revealing that the 55-billion-transistor device includes 64 cores, runs at 2.6GHz clock speed, can address DDR5 RAM and 300GB/sec max memory bandwidth, and employs 256-bit Scalable Vector Extensions.
The chips were offered as a tech preview to select customers. And on Monday, AWS made them available to all comers in a single instance type named C7g.
[2]
EC2's C-series instances are billed as ideal for compute intensive tasks. The series is now in its seventh generation – and the only seventh-gen instance uses Graviton3. Intel Xeons and AMD EPYCs are currently confined to sixth-gen instance types.
[3]
[4]
Take that , you x86 dinosaurs.
[5]A peek into Gigabyte's GPU Arm for AI, HPC shops
[6]AMD reveals 5nm Ryzen 7000 powered by Zen 4 cores
[7]The 'substantial contributions' Intel has promised to boost RISC-V adoption
[8]Intel's Habana unit reveals new Nvidia A100 challengers
The C7g instances offer eight sizes, with 1, 2, 4, 8, 16, 32, 48, and 64 vCPUs.
The Register has looked up hourly prices for the C7 instance, the C6 instance that uses the Graviton 2, and the C-series instances running the third-gen Xeon and EPYC processors. We used the US West (Oregon) region as our guide, as it is one of just two regions currently offering the Graviton3. Our research considered instances running the same number of vCPUs offered by the C7 instance type.
As the table below shows, Graviton3 instances cost more than Graviton2-powered rent-a-servers, but less than their x86 competitors. AWS offers other ways to consume its infrastructure at lower prices.
vCPUs
C7g Graviton3
C6i 3rd-gen Xeon
C6a 3rd-gen EPYC
C6g Graviton2
1
$0.036
N/A
N/A
$0.034
2
$0.073
$0.085
$0.077
$0.068
4
$0.145
$0.170
$0.153
$0.136
8
$0.290
$0.340
$0.306
$0.272
16
$0.580
$0.680
$0.612
$0.544
32
$1.160
$1.360
$1.224
$1.088
48
$1.740
$2.040
$1.836
$1.632
64
$2.320
$2.720
$2.448
$2.176
The AWS [9]announcement of Graviton3 going into production mentions that Snap Inc., operator of Snapchat and Bitmoji, plans to adopt the new silicon because it has proven faster than Graviton2. That is not great news for Google Cloud, as Snap signed a five-year, $2 billion deal with the ad giant in 2017. Five years later we discover that the social network operator has gone multi-cloud!
AWS's post announcing the C7 instances points out that migrating to Gravitons from x86 isn't hard for many workloads – especially if those workloads are AWS services like its own container and database services.
[10]
Which is utterly self-serving, but also an indicator that, as AWS brings more of its own services to its own silicon, trying Graviton silicon will become less onerous.
The timing of AWS's Graviton3 announcement appears not to have been co-incidental, as it came a few hours before Nvidia revealed [11]server designs based on its own high-end processors .
Perhaps AWS hoped to steal some of Nvidia's thunder.
[12]
Yet the combined effect of the two announcements may be more significant. Together they demonstrate that enterprise computing buyers can now consider multiple mature, well-backed technology choices beyond the x86 architecture. And there is more to come as Microsoft, Oracle, and others introduce their own Arm-powered servers, not t mention the imminent arrival of [13]SmartNICs as accessible on-prem technology. ®
Get our [14]Tech Resources
[1] https://www.theregister.com/2021/12/01/aws_reinvent_graviton_3/
[2] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=2&c=2YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0
[3] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0
[4] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0
[5] https://www.theregister.com/2022/05/23/gigabyte_intros_arm_server/
[6] https://www.theregister.com/2022/05/23/amd_zen4_am5_mendocino_computex/
[7] https://www.theregister.com/2022/05/17/intel_riscv_contributions/
[8] https://www.theregister.com/2022/05/10/intels_habana_unit_reveals_new/
[9] https://aws.amazon.com/blogs/aws/new-amazon-ec2-c7g-instances-powered-by-aws-graviton3-processors/
[10] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=4&c=44YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0
[11] https://www.theregister.com/2022/05/24/nvidia_cpu_hpc/
[12] https://pubads.g.doubleclick.net/gampad/jump?co=1&iu=/6978/reg_offprem/paasiaas&sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&tile=3&c=33YoysxkqaGfpODq7uScRnjQAAABU&t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0
[13] https://www.theregister.com/2022/05/20/smartnic_cloud_datacenter/
[14] https://whitepapers.theregister.com/
jon90909
The lack of benchmarks in this article is deafening.
Persona
At $2.32 to rent 64 vCPUs for an hour a prospective user could try it for themselves and make their own decision based on their workload rather than trusting a benchmark.
Charlie Clark
The discount is hardly sufficient to warrant such trials. But, as usual, the CPU is only a small part of the picture: unless you're transcoding video, etc. RAM and IO will be more important.
And citing Snap as a customer is hardly going to inspire anyone; Snap who?
Take that, you x86 dinosaurs
We can take that. The Graviton3 is not the comet to end all x86s.
Don't worry, we'll still be around for a loooong time.