AMD Ryzen™ AI for Business

1. Ryzen™ AI is defined as the combination of a dedicated AI engine, AMD Radeon™ graphics engine, and Ryzen processor cores that enable AI capabilities. OEM and ISV enablement is required, and certain AI features may not yet be optimized for Ryzen AI processors. Ryzen AI is compatible with: (a) All Ryzen AI 300 Series processors (b) AMD Ryzen 7040 and 8040 Series processors except Ryzen 5 7540U, Ryzen 5 8540U, Ryzen 3 7440U, and Ryzen 3 8440U processors; and (c)all AMD Ryzen 8000G Series desktop processors except the Ryzen 5 8500G/GE and Ryzen 3 8300G/GE. Please check with your system manufacturer for feature availability prior to purchase. GD-220c.
2. Based on AMD Ryzen™ 9 8945HS Processor combined TOPS of CPU, GPU, and NPU engines.
3. Based on testing by AMD Engineering as of 10/12/23, on a test system configured with an AMD Ryzen 7 7840U processor with Ryzen AI enabled, Radeon 780M Graphics, 16GB RAM, and Windows 11 Pro vs. a similarly configured system with Ryzen AI disabled, to compare the respective NPU and GPU resource utilization scores on select internal AMD AI models running concurrently: Depth Estimation, Eye Gaze Correction, Super Resolution, and Scene Detection. PC manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers. PHXP-56
4. Based on testing by AMD Engineering as of 10/24/23, on a test system configured with an AMD Ryzen 7 7840U processor with Ryzen AI enabled, Radeon 780M Graphics, 16GB RAM, and Windows 11 Pro vs. a similarly configured system with Ryzen AI disabled, to compare latency using the following select AMD internal AI models, run concurrently: Depth Estimation, Eye Gaze Correction, Super Resolution, and Scene Detection vs. the same processor configuration with Ryzen AI disabled. PC manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers. PHXP-59
5. HWK-32. Testing as of Dec 2023 by AMD Performance Labs on a test system configured with a Ryzen 7 8840U, integrated Radeon 780M graphics, 16GB DDR5 RAM, Samsung 980 Pro 1TB NVMe, and Windows 11 Pro vs. a similarly configured system with an Intel Core Ultra 7 155H on an MSI Prestige 16 AI notebook, with integrated Iris Arc Graphics, 32GB DDR5 RAM, 1TB SSD, and Windows 11 22H2 to test performance on using the following AI models: MobileNetv3, ESRGAN, Yolov8, Deeplabv3, StableDiffusion1.5 (Olive), DaVinci Resolve – HD to UHD 2x Enhanced, Procyon AI Benchmark – Float16, Procyon AI Benchmark – Float32. System manufacturers may vary configurations, yielding different results. HWK-32.
6. HWKP-30. Testing as of 4/7/24 by BOXX Technologies, commissioned by AMD, on an HP Zbook Power G11 with an AMD Ryzen™ 9 PRO 8945HS processor (45W) with Nvidia RTX 3000 Ada graphics, 32GB RAM, 1TB NVMe SSD, Microsoft Windows 11 Professional (x64) vs. a Dell Precision 3591 with Intel Core Ultra 9 185H processor (45W), Nvidia RTX 2000 Ada graphics, 64GB RAM, 1TB SSD, Microsoft Windows 11 Professional (x64). The following applications were tested in Best Performance Mode: Dassault Solidworks 2022 CPU Composite, PTC Creo v9 CPU Composite, Keyshot 2023 CPU, Topaz Labs Video AI Gaia 4X 4K, V-RAY v6 CPU vsamples, SPEC Workstation Media and Entertainment, SPECviewperf 2020 v3.1 Composite Geomean, SPEC Workstation GPU Compute.  Results may vary.  HWKP-30.
7. Testing as of 1/15/24 by AMD Internal Labs, utilizing a Dell Precision with Intel 13th Gen Intel© Core™ i9-13900H processor, Intel integrated graphics, 64GB RAM, 1TB SSD and Windows 11 Pro and a HP HP ZBook Power with AMD Ryzen 9 PRO 7940HS processor,  Integrated Radeon 780M graphics, 64GB RAM, 1TB SSD, Windows 11 Pro, using the AMuse benchmark to compare the integrated graphics performance on text to image AI inference. PC manufacturers may vary configurations yielding different results. Results may vary. PHXP-78
8. Testing as of 1/15/24 by AMD Internal Labs, utilizing a Dell Precision with Intel 13th Gen Intel© Core™ i9-13900H processor, Intel integrated graphics, 64GB RAM, 1TB SSD and Windows 11 Pro and a HP HP ZBook Power with AMD Ryzen 9 PRO 7940HS processor,  Integrated Radeon 780M graphics, 64GB RAM, 1TB SSD, Windows 11 Pro, using the Davinci Resolve AI test bench to compare the integrated graphics performance on several AI accelerated tasks within Davinci Resolve. PC manufacturers may vary configurations yielding different results. Results may vary. PHXP-77
9. Testing as of 1/15/24 by AMD Internal Labs, utilizing a Dell Precision with Intel 13th Gen Intel© Core™ i9-13900H processor, Intel integrated graphics, 64GB RAM, 1TB SSD and Windows 11 Pro and a HP HP ZBook Power with AMD Ryzen 9 PRO 7940HS processor,  Integrated Radeon 780M graphics, 64GB RAM, 1TB SSD, Windows 11 Pro, using the Davinci Resolve AI test bench to compare the integrated graphics performance on several AI accelerated tasks within Davinci Resolve. PC manufacturers may vary configurations yielding different results. Results may vary. PHXP-79
10. HWKP-29. Testing as of 3/26/24 by AMD Performance Labs on a HP EliteBook 845 G11 with an AMD Ryzen™ 7 PRO 8840U processor 15W, integrated Radeon™ 780M graphics, 32GB RAM (2X16GB) 2800MHz, 512GB NVMe SSD, Microsoft Windows 11 Professional vs. a Dell Latitude 7450 with Intel Core Ultra 7 165U processor 15W (vPro enabled), Intel Iris Xe Graphics, 16GB RAM (2X8GB) 29866.7 MHz, 512GB NVMe SSD, Microsoft Windows 11 Professional vs. a Dell Latitude 7450 with Intel Core Ultra 7 165H processor 28W (vPro enabled), Intel Arc Graphics, 16GB RAM (2X8GB) 33600.0 MHz, 512GB NVMe SSD, Microsoft Windows 11 Professional vs a Dell XPS 9440 with Intel Core Ultra 7 155H processor 28W, Intel Arc Graphics, 16GB RAM (2X8GB) 6400MHz, 1TB NVMe SSD, 69Wh battery, Microsoft Windows 11 Professional. All systems run in Best Power Efficiency mode using the following applications: Microsoft Teams with AI enabled (All Windows Studio Effects enabled) + Procyon Office Productivity Overall benchmark measuring Wall power consumed (watts). Each Microsoft Teams call consists of 9 participants (3X3). Laptop manufacturers may vary configurations yielding different results. HWKP-29
11. PHX-59. Testing as of Feb 2023 by AMD. Sustained performance average of multiple runs with specimen prompt "Write me a story about an orange cat called mr whiskers". All tests conducted on LM Studio 0.2.16. Performance may vary. Market price retrieved on 3/4/2023 (Amazon, US). Phoenix: HP Pavilion Plus Laptop 14-ey0xxx, Ryzen 7 7840U 15W TDP, 16GB LPDDR5 6400, Windows 23H2 22631.3155, Adrenalin Driver 24.2.1. Meteor Lake: Acer Swift SFG14-72T, Intel Core Ultra 7 155H 28W TDP, 16GB LPDDR5 6400, Windows 23H2 22631.3155, Driver 31.0.101.5333. PHX-59.
12. As of May 2023, AMD has the first and only available dedicated AI engine on an x86 Windows processor, where 'dedicated AI engine' is defined as an AI engine that has no function other than to process AI inference models and is part of the x86 processor die. For detailed information, please check: https://www.amd.com/en/products/ryzen-ai. PHX-3.

• GD-202: Microsoft Pluton is a technology owned by Microsoft and licensed to AMD. Microsoft Pluton is a registered trademark of Microsoft Corporation in the United States and/or other countries. Learn more at https://www.microsoft.com/security/blog/2020/11/17/meet-the-microsoft-pluton-processor-the-security-chip-designed-for-the-future-of-windows-pcs/. Microsoft Pluton security processor requires OEM enablement. Check with the OEM before purchase. AMD has not verified the third-party claim.
• FIPS 140-3 Level 2 certification under test.
• GD-206: Full system memory encryption with AMD Memory Guard is included in AMD Ryzen™ PRO, AMD Ryzen™ Threadripper PRO, and AMD Athlon™ PRO processors. PP-3. Full system memory encryption with AMD Memory Guard is included in AMD Ryzen PRO, AMD Ryzen Threadripper PRO, and AMD Athlon PRO processors. Requires OEM enablement. Check with the system manufacturer prior to purchase.
• GD-72: The AMD Secure Processor is a dedicated on-chip security processor integrated within each system-on-a-chip (SoC) and ASIC (Application Specific Integrated Circuit) designed by AMD. It enables secure boot with root of trust anchored in hardware, initializes the SoC through a secure boot flow, and establishes an isolated Trusted Execution Environment.
• SMB Windows 11 Survey Report. Techaisle, February 2022. Windows 11 results are in comparison with Windows 10 devices.
• Based on AMD labs testing in November 2022, on a system configured with a Radeon RX 7900 XTX GPU, driver 31.0.14000.24040, AMD Ryzen 9 5900X CPU, 32GB DDR4-3200MHz, ROG CROSSHAIR VIII HERO (WI-FI) motherboard, set to 300W TBP, on Win10 Pro, versus a similarly configured test system with a 300W Radeon 6900 XT GPU and driver 31.0.12019.16007, measuring FPS performance in select titles. Performance per watt is calculated using the manufacturers’ stated total board power (TBP) of the AMD GPUs listed herein. System manufacturers may vary configurations, yielding different results. RX-816.
• Based on AMD internal measurements, November 2022, comparing the Radeon RX 7900 XTX at 2.505 GHz boost clock with 96 CUs issuing 2X the Bfloat16 math operations per clocks vs. the RX 6900 XT GPU at 2.25 GHz boost clock and 80 CUs issue 1X the Bfloat16 math operations per clock. RX-821.
• Based on a November 2022 AMD internal performance lab measurement of rays with indirect calls on RX 7900 XTX GPU vs. RX 6900 XT GPU. RX-808
• Based on AMD performance lab testing as of September 28, 2023, using the Chromium Compilation 115.0.5740 benchmark, the Unreal Engine 5.1 compilation benchmark, the PugetBench for Premiere Pro v0.98.0 benchmark, the PugetBench for Adobe AfterEffects v0.95.7 benchmark, the VRay CPU performance benchmark, the SPECapc Maya 2023 CPU composite metric, the Keyshot Viewer 2023.1_12.0.0.186, the SPECapc for Solidworks 2022 CPU composite metric, the Corona rendering (Rays/Sec) benchmark, the Revit RFO model creation benchmark, Cadalyst AutoCAD 2022 benchmark, and the Puget Metashape total processing time (Rock Model) to compare the performance of an AMD Ryzen Threadripper 7980X processor in a reference system configured with 8x32GB DDR5, NVIDIA Quadro RTX A5000 graphics, 1TB SSD, Win 11 vs. a similarly configured BOXX workstation with an Intel Xeon w9-3495X processor. Workstation manufacturers may vary configurations, yielding different results. Results may vary. SPP-09
• Commissioned study delivered by Forrester Consulting “The Total Economic Impact™ of Windows 11 Pro Devices”, December 2022. Note, quantified benefits reflect results over three years combined into a single composite organization that generates $1 billion in annual revenue, has 2,000 employees, refreshes hardware on a four-year cycle, and migrates the entirety of its workforce to Windows 11 devices.
• Principled Technologies Report: https://www.principledtechnologies.com/AMD/Ryzen-7-mixed-CPU-deployment-1123.pdf
• Includes AMD high-performance CPU and GPU accelerators used for AI training and high-performance computing in a 4-Accelerator, CPU-hosted configuration. Goal calculations are based on performance scores as measured by standard performance metrics (HPC: Linpack DGEMM kernel FLOPS with 4k matrix size. AI training: lower precision training-focused floating-point math GEMM kernels such as FP16 or BF16 FLOPS operating on 4k matrices) divided by the rated power consumption of a representative accelerated compute node, including the CPU host + memory and 4 GPU accelerators.
• EPYC-030a: Calculation includes 1) base case kWhr use projections in 2025 conducted with Koomey Analytics based on available research and data that includes segment specific projected 2025 deployment volumes and data center power utilization effectiveness (PUE) including GPU HPC and machine learning (ML) installations and 2) AMD CPU and GPU node power consumptions incorporating segment-specific utilization (active vs. idle) percentages and multiplied by PUE to determine actual total energy use for calculation of the performance per Watt. 13.5x is calculated using the following formula: (base case HPC node kWhr use projection in 2025 * AMD 2023 perf/Watt improvement using DGEMM and TEC +Base case ML node kWhr use projection in 2025 *AMD 2023 perf/Watt improvement using ML math and TEC) /(2020 perf/Watt * Base case projected kWhr usage in 2025). For more information, www.amd.com/en/corporate-responsibility/data-center-sustainability.
• Reported data includes Scope 1 and 2 GHG emissions (base year 2020). Based on AMD calculations that are third-party verified (limited level assurance).
• Manufacturing suppliers are suppliers that AMD buys from directly and that provide direct materials and/or manufacturing services to AMD.
• AMD calculations are third-party verified (limited level assurance) based on data supplied by our direct manufacturing suppliers which is not independently verified by AMD.
• Max boost for AMD Ryzen processors is the maximum frequency achievable by a single core on the processor running a bursty single-threaded workload. Max boost will vary based on several factors, including, but not limited to: thermal paste; system cooling; motherboard design and BIOS; the latest AMD chipset driver; and the latest OS updates. GD-150
• Trade-in values will vary based on the condition, year, and configuration of your eligible trade-in device. Not all devices are eligible for credit. You must be at least 18 years old to be eligible to trade in for credit. Trade-in value may be applied toward qualifying new device purchase. Actual value awarded is based on receipt of a qualifying device matching the description provided when estimate was made. Sales tax may be assessed on full value of a new device purchase. AMD or its trade-in partners reserve the right to refuse or limit quantity of any trade-in transaction for any reason. More details are available from AMD’s trade-in partner for trade-in and recycling of eligible devices. Restrictions and limitations may apply. Terms & conditions apply.
• Only the English version of this document has legal effect. Any translations of this document to other languages are provided for your convenience only.

©2024 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, Ryzen™, XDNA™, Threadripper™, Radeon™, RDNA™, and combinations thereof are trademarks of Advanced Micro Devices, Inc. Microsoft and Windows are registered trademarks of Microsoft Corporation in the US and/or other countries. Other product names used herein are for identification purposes and may be trademarks of their respective owners. Certain AMD technologies may require third-party enablement or activation. Supported features may vary by operating system. Please confirm with the system manufacturer for specific features. No technology or product can be completely secure.