⋮  

Official AMD Ryzen Launch Day Slide Deck Leaked – Ryzen Reviews To Hit Web Tomorrow, Market Availability in 24 Hours

Author Photo
Mar 1, 2017
18Shares
Submit

Tomorrow is the day we have all been waiting for several years, the AMD Ryzen processors will officially be available on the market and we will get to see several launch day reviews from major tech sites. AMD’s Ryzen journey has been long, but in less than 24 hours, we will get our real taste of the high-end desktop CPUs for a high-end, enthusiast platform.

AMD Ryzen CPU Architecture Fully Detailed – Wider, High-Performance and Efficient Core Design With IPC Gains Beyond 50%

UPDATE: The full AMD Ryzen launch day slide deck has leaked out. You can find slides from the entire presentation posted below:

amd-epyc-8Related Alleged AMD EPYC ‘Rome’ 7nm Based 64 Core Processor Performance Leaks Out – Scores an Incredible 12,500 Points in Cinebench Multi-Tasking Benchmark

While we still have 24 hours left until the launch, Videocardz went ahead to leak the full launch day slides of the Ryzen CPU architecture. We know every crucial detail about the Ryzen CPU architecture but let’s take a quick recap of the details.

To start off with, Ryzen is based on the latest 14nm FinFET node. The only two foundries that have this node are GlobalFoundries and Samsung but AMD is using the former to develop Zen chips. The Ryzen core features 52% more instructions per clock compared to the Excavator core which exceeds AMD’s goal of delivering 40% IPC gain with Zen chips.

intel-8th-generation-core-processors-with-amd-radeon-rx-vega-m-graphics_33Related Intel CPU Shortages Predicted, AMD to Reap Benefit Amid Analyst Upgrades

The Excavator core is featured on AMD’s Carrizo and Godavari processors. The large jump in IPC helps AMD achieve performance parity with Intel chips. In fact, AMD already demoed an 8 core Ryzen processor based on Zen against a Broadwell-E 8 core chip. AMD delivered better synthetic and gaming performance than their competitor’s enthusiast chip at a TDP of just 95W.

There are several key performance and power improvements featured on the new Zen architecture. A high-level overview of the Ryzen CPU can be seen below.

AMD Ryzen High Level Overview

  • Two threads per core
  • 8 MB shared L3 cache
  • Large, unified L2 cache
  • Micro-op Cache
  • Two AES units for security
  • 14nm FinFET Transistors

AMD Ryzen Core Design and Core Engine

The basic building block of Ryzen is the core complex. The core complex comprises of four cores connected to an L3 cache. The L3 cache is 16-Way associated and makes up a total of 8 MB (mostly exclusive of L2 cache). The L3 cache is sliced into four, each comprising of two 1 MB L3 sub-slices. All cores can access these cache blocks with the same average latency speed.

The AMD Zen CPU complex is designed with a 14nm process and features 4 cores and 8 threads. The CPU complex spans an area of 44mm2 which is smaller than the 49mm2 featured on their competitors latest 14nm chips (Broadwell-E). The CPU complex is fitted with 512 KB (1.5mm2/core) L2 cache and 8 MB (16 mm2) L3 cache.

The cores themselves feature two threads each. The core complex hence comprises 8 threads while the 8 core SKUs comprise 16 threads. AMD can combine multiple CPU complexes to create high core count CPUs all the way from single (4/8) to octa-complex (32/64) SKUs.

On each core, branch misdirect is improved and the branch prediction has been improved with two branches per BTB. The large Op cache helps improve throughput and latency at the same time. The integer cluster in each Zen core has six pipes, four ALUs, Arithmetic Logic Units, and two AGUs which is short for Address Generation Units.

These AGUs can perform two 16-byte loads and one 16-byte store per cycle via a 32 KB 8-way set associative write-back L1 data cache. According to AMD the move from a write-through to a write-back cache has noticeably reduced stalls in several types of code paths. The load/store cache operations cache in Zen also reportedly exhibit lower latency compared to Excavator.

AMD has tried to improve Zen with a larger dispatch of 6 vs 4 on Excavator. Instruction schedulers for integer and floating point have also increased to 84 and 96, respectively. The FPU is now an quad issue while queue sizes for retire, load and store have increased to 192, 72, 44 compared to 128, 44, 32 on Excavator.

The two floating point units on the new core consist of 4 pipes with 128 FMACs per FPU. There are two FADD and two FMUL units for calculations on the FPU. The FPU consists of a 2-level scheduling queue with a 160 entry register file, 8-Wide retire and a single pipe for 128b store. It has its own two AES units and is SSE, AVX1,  AVX2, AES, SHA and legacy MMX compliant.

AMD Ryzen With SMT (Simultaneous Multi-Threading) Support

One of the most anticipated arrivals on the new core is SMT support. This brings the design level much closer to Intel’s implementation. The SMT design offers increased throughput by executing two threads simultaneously. These virtual threads will appear as independent cores to software and allow more execution resources for applications.

Along with the SMT support, Zen also features support for several new instructions. These include ADX, RDSEED, SMAP, SHA1, XSAVEC, CLZERO and PTE Coalescing. AMD also supports all the standard ISA that are mentioned above.

AMD Ryzen High Bandwidth, Low Latency Cache System

AMD has been talking about a disruptive cache system on their new core for a while. With the details finally out, we can now better understand this system. The cache hierarchy is made up of a fast private L2 cache on each core (512 KB L2 L+D 8-Way) and a fast shared L3 cache (8 MB L3 L+D 16-Way).

Performance is one thing but one place where AMD has really lacked is efficiency. With Zen, that is going to change. Zen has much higher efficiency than Excavator which is a highly tuned design in itself. This is achieved through the use of aggressive clock-gating techniques on multi-level regions inside the core block. Some of the features that help achieve lower power on Zen include:

AMD’s precision boost system is a combination of 1000+ sensors per core complex that identify the optimal operation point of the processors. There are 48 on-die high speed power supply monitors, 20 thermal diodes and 9 high speed droop detectors which result in a total efficiency gain of 2.29x when compared to previous generation architectures from AMD.

Precision boost enables the core to operate and can also push to higher operating points if reliability and conditions such as cooling allow (XFR – Extended Frequency Range).

AMD Ryzen Low Power Features:

  • Aggressive Clock Gating with multi-level regions
  • Write Back L1 Cache
  • Large OP Cache
  • Stack Engine
  • Move Elimination
  • Power Focus from Project Inception
  • Low Power design Methodologies
CPU Microarchitecture AMD Phenom II / K10 AMD BD/PD AMD SR/XV AMD Zen Intel Skylake
Instruction Decode Width 3-wide 4-wide 8-wide 4-wide 4-wide
Single Core Peak Decode Rate 3 instructions 4 instructions 8 instructions 4 instructions 4 instructions
Dual Core Peak Decode Rate 6 instructions 4 instructions 8 instructions 8 instructions 8 instructions

AMD Ryzen 7 Series CPUs – Flagship AMD 7 1800X With 8 Cores, 16 Threads, 4 GHz Boost Clocks

The AMD 8 core range will feature the fastest “X” variant in the lineup. This processor will be known as the AMD 7 1800X and will feature 8 cores and 16 threads. This model is expected to operate at base clocks of 3.6 GHz and boost clocks of 4.0 GHz. The performance of this processor should be on par with Intel’s Core i7 6900K. Other details include an L2 + L3 cache of 20 MB (4 MB + 16 MB) and a TDP of 95W. The chip will have enthusiast level pricing at $499 which compared to Intel’s 6900K ($1000 US+) is a great deal.

The rest of the processors in the Ryzen 7 family are also 8 core and 16 threaded variants. The Ryzen 7 series has clock speeds ranging from 3.0 GHz up to 3.6 GHz. The processors include Ryzen 7 PRO 1800, Ryzen 7 1700X, Ryzen 7 1700 (Gaming and CPU Benchmarks here) and Ryzen 7 PRO 1700. The AMD 1800X also managed to break the 8 core Cinebench R15 performance world record last week, more details here.

AMD Ryzen 7 Series Processor Lineup:

AMD Ryzen CPU Model Cores/Threads Base Clock Boost Clock L3 Cache TDP Socket Price
Ryzen 7 1800X 8/16 3.6 GHz 4.0 GHz 16 MB 95W-SR3+ AM4 $499 US
Ryzen 7 Pro 1800 8/16 TBD TBD 16 MB 95W AM4 $449 US
Ryzen 7 1700X 8/16 3.4 GHz 3.8 GHz 16 MB 95W-SR3+ AM4 $399 US
Ryzen 7 1700 8/16 3.0 GHz 3.7 GHz 16 MB 65W AM4 $329 US
Ryzen 7 Pro 1700 8/16 TBD TBD 16 MB 65W AM4 $299 US

AMD Ryzen 7 1700X Gaming Benchmarks:

The first slide shows us the gaming performance of AMD’s Ryzen 7 1700X ($399 US) processor against Intel’s Core i7 6800K ($434 US) processor. We see that while the Intel chip generally leads in more game titles than the AMD counterpart, the difference is so small that the extra price of the Intel chip doesn’t seem to be of great value. All games were tested at maximum settings at 1440p tests. We have made charts so that you can easily compare performance of the both chips as the image is a little blurred. The performance was evaluated with a NVIDIA GeForce GTX 1080 graphics card.

AMD Ryzen 7 1700X Vs Intel Core i7 6800K Gaming Benchmarks Average FPS:

Game Title AMD Ryzen 7 1700X Intel Core i7 6800K
GTA V (DX11) 139 FPS 145 FPS
Alien: Isolation (DX11) 194 FPS 200 FPS
Battlefield 4 (DX12) 111 FPS 115 FPS
Ashes of The Singularity (DX12) 55 FPS 56 FPS
Civilization VI (DX12) 62 FPS 79 FPS
Doom (Vulkan) 127 FPS 123 FPS

AMD Ryzen 7 1700X Vs Intel Core i7 6800K Gaming Benchmarks 99th% FPS:

Game Title AMD Ryzen 7 1700X Intel Core i7 6800K
GTA V (DX11) 71 FPS 52 FPS
Alien: Isolation (DX11) 123 FPS 143 FPS
Battlefield 4 (DX12) 75 FPS 79 FPS
Ashes of The Singularity (DX12) 40 FPS 39 FPS
Civilization VI (DX12) 50 FPS 54 FPS
Doom (Vulkan) 102 FPS 102 FPS

AMD Ryzen 7 1700 Gaming Benchmarks:

The second performance slide shows the AMD Ryzen 7 1700 up against the Intel Core i7 7700K processor. These chips are $329 US and $339 US respectively. Again, we see the Intel chip faster in most benchmarks but the Ryzen chip is a bit cheaper and has higher multi-threaded performance for the other workloads aside of gaming. The performance was evaluated with a NVIDIA GeForce GTX 1070 graphics card.

AMD Ryzen 7 1700 Vs Intel Core i7 7700K Gaming Benchmarks Average FPS:

Game Title AMD Ryzen 7 1700 Intel Core i7 7700K
GTA V (DX11) 167 FPS 190 FPS
Alien: Isolation (DX11) 163 FPS 165 FPS
Battlefield 4 (DX12) 94 FPS 95 FPS
Ashes of The Singularity (DX12) 44 FPS 44 FPS
Civilization VI (DX12) 53 FPS 73 FPS
Doom (Vulkan) 101 FPS 98 FPS

AMD Ryzen 7 1700 Vs Intel Core i7 7700K Gaming Benchmarks 99th% FPS:

Game Title AMD Ryzen 7 1700 Intel Core i7 7700K
GTA V (DX11) 56 FPS 85 FPS
Alien: Isolation (DX11) 114 FPS 117 FPS
Battlefield 4 (DX12) 67 FPS 65 FPS
Ashes of The Singularity (DX12) 30 FPS 30 FPS
Civilization VI (DX12) 48 FPS 57 FPS
Doom (Vulkan) 78 FPS 77 FPS

AMD’s Ryzen 7 processors will launch tomorrow followed by mainstream chips in Q2 2017 and budget-tier chips in 2H 2017. Retailers have already dropped prices on several Intel processors which hints at the start of a major price war which will be seen between the two CPU rivals after several silent decades. For the full AMD AM4 motherboard lineup, visit our detailed round-up on this page.

Submit