Introduction

AMD is back in the desktop CPU game with its Ryzen family of processors, thanks to successes with per-core performance and energy-efficiency improvements brought about by its "Zen" micro-architecture. The company launched its Ryzen processor family with the top-end Ryzen 7 series, which consists of eight-core models that start at $329, going all the way up to $499. These chips do manage to make you think twice before choosing an Intel Core i7-7700K quad-core chip, and make the Core i7 "Broadwell-E" series look terrible, all the way up to the $1,199 i7-6900K. Ahead of Summer 2017, when PC gamers hit the stores for hardware upgrades, AMD is launching a new line of Ryzen processors at price points targeting them, with the new Ryzen 5 series.

The Ryzen 5 series from AMD competes with the entire spectrum of Intel's Core i5 quad-core "Kaby Lake" series, at prices ranging from $169 to $249. This puts Intel's high-volume Core i5-7600K and value-oriented i5-7400 in its crosshairs. Carved out of the same 14 nm "Summit Ridge" silicon as the eight-core Ryzen 7 series, the Ryzen 5 series consists of six-core and quad-core SKUs, which are further bolstered by SMT (simultaneous multi-threading) and unlocked base-clock multipliers across the board. SMT (and its Intel-implementation, HyperThreading) is something quad-core Core i5 parts lack, and unlocked multipliers is reserved only for the i5-7600K quad-core and the $189 i3-7350K dual-core. What's more, the six-core Ryzen 5 parts feature a staggering 16 MB of L3 cache (compared to the paltry 6 MB of the price-comparable Core i5 quad-core parts), and the quad-core parts feature a decent 8 MB. Given AMD has made significant strides in improving per-core performance and the software ecosystem finally taking advantage of more than 4 logical CPUs, the Ryzen 5 series looks extremely exciting on paper.



While the Ryzen 5 series is led by the $249 six-core Ryzen 5 1600X, which AMD claims will compete with not just the price-matched Core i5-7600K, but also punch above its weight against the $329 Core i7-7700K in some tests, a more exciting part with implications in particular for the PC-gaming crowd is the quad-core Ryzen 5 1500X. This chip is priced at $189, a price at which Intel is selling the overclocker-friendly dual-core i3-7350K and its slowest quad-core i5-7400 part. With the i3-7350K, Intel is hoping that two highly clocked "Kaby Lake" cores with HyperThreading make for a sufficiently fast gaming-PC processor. The Core i5-7400 gives you four cores, but no HyperThreading and clock speeds of 3.00 GHz, with 3.50 GHz Turbo Boost speeds. The Ryzen 5 1500X, in comparison, gives you not just four cores, but also SMT, enabling 8 logical CPUs (something you'd have to shell out upwards of $300 on the Intel lineup for), 8 MB of L3 cache, and clock speeds of 3.50 GHz with 3.70 GHz TurboCore frequency, and the XFR (extended frequency range) feature enabling higher automated overclocks, depending on the efficacy of your CPU cooling.

A Closer Look

The Ryzen 5 1500X retail package includes AMD's new Wraith Spire cooling solution. The cooler features a large cylindrical heatsink with radially projecting fins, which is ventilated by a large fan. AMD has optimized the fan for low noise.


Topside, the Ryzen chip looks quite similar to every AMD desktop processor since Athlon64. A large, thick integrated heatspreader tops off the chip. Underneath, you see the chip's PGA (pin grid array). AM4 consists of 1,331 pins (missed opportunity to add 6 more ground pins), and these pins are a lot finer those you find on AM3+ FX-series processors, so handle these chips with extreme care.


AM4 still has a rectangular cooler mount-hole layout (as opposed to square ones on Intel LGA platforms). AMD should have switched to a square layout to make it easier to orient tower-type coolers to blow hot air out the rear of the case. Current AM4-ready tower-type coolers have elaborate retention module kits that let you do that. Most popular cooler vendors are either selling or giving away AM4 retention modules for free. You often also have to remove the plastic retention module motherboards ship with to install certain kinds of coolers.

The "Zen" Architecture

The oldest reports about AMD working on the "Zen" architecture date back to 2012, when AMD re-hired CPU core designer Jim Keller, credited with the original winning K8 and K9 architecture designs, to work on a new core architecture to succeed "Bulldozer." AMD continued to invest in the "Bulldozer" IP in the form of incremental core updates, hoping that trends in the software industry towards parallelization could improve, giving it a big break in price/performance. Those trends, in the form of DirectX 12 and Vulkan 3D APIs being multi-core friendly, came in a tad late (towards late 2016). Four years of work by a team dedicated to its development, led by Jim Keller, resulted in the "Zen" core.


At the heart of the "Zen" core are two very important innovations - a very "intelligent" branch-prediction system that uses neural nets (yes, of the same kind that power deep-learning machinery) to predict branches in code and load the most appropriate instructions and allocation of core resources; and there's a 1.5X increase in issue width and execution resources, besides a 1.75X increase in the instruction scheduler window. Intel had been beating AMD in core performance and efficiency in exactly these two areas, and AMD finally addressed it instead of throwing in too many more hardware resources without addressing the branch-prediction issues. "Zen" also features an up-to-date ISA instruction set, including AVX2, FMA3, and SHA.


All Ryzen processors are based on the 14 nm "Summit Ridge" silicon built at GlobalFoundries' swanky new facility in Upstate New York. One look at the die shot will show you that the CPU cores are clumped in two groups each. These groups are called quad-core complex (CCX). There is no specific reason as to why AMD chose groups of four cores, other than four being a manageable number of cores for AMD's product managers. Each individual core in a CCX can be disabled and doesn't share anything with its neighboring core except for an 8 MB block of L3 cache. Each core has its own dedicated 512 KB L2 cache. The two CCX units talk to each other over AMD Infinity Fabric, a new high-bandwidth interconnect that succeeds HyperTransport.

The AM4 Platform

What sets "Summit Ridge" apart from Intel dies, such as "Kaby Lake" or "Broadwell-E," is that it is a full-fledged SoC (system-on-chip). It integrates both the northbridge and southbridge. In addition to memory and PCIe, socket AM4 processors also put out USB 3.0 and two SATA 6 Gb/s ports. The platform still has something called a "chipset," but it only serves to increase connectivity options, such as adding more SATA ports, USB 3.1 ports, and a few more general-purpose PCIe lanes. On Intel's platforms, the PCH (platform controller hub) serves the functions of the southbridge, while the northbridge is fully integrated with the processor.



AMD has five chipsets for Ryzen - the X370 for high-end desktops, which supports proprietary multi-GPU technologies such as NVIDIA SLI; the mid-tier B350 chipset with a slimmer connectivity feature set, and the entry-level A320 chipset for low-cost desktops. There's also the X300 and A300. We doubt you can even call these a chipset because they don't even have an A-link chipset bus to the SoC and only talk over legacy SPI pins, and they have simple components to keep the platform ticking. What sets the two apart is lack of CPU overclocking support on the A300. On machines with the X300 and A300 (such as SFF desktops), all the connectivity is handled by the SoC.