AMD Cezanne Silicon

Unlike the other Ryzen 5000 desktop processors that are based on the Vermeer multi-chip module (MCM), the Ryzen 5000G processors with integrated graphics are based on a monolithic die codenamed "Cezanne." Built entirely on the 7 nm silicon fabrication process, it has a die area of 180 mm² with a transistor-count of 10.7 billion. Designed to be an SoC in its own right, Cezanne combines an 8-core CPU based on the Zen 3 microarchitecture with an iGPU based on Vega, along with a dual-channel DDR4 integrated memory controller, and I/O based on PCI-Express Gen 3. The Ryzen 7 5700G maxes out this silicon by enabling all 8 cores and 16 threads of the CPU, and all 8 compute units of the Vega iGPU.

The biggest change Cezanne brings over last year's "Renoir" silicon (which did not launch in the retail segment) is the CPU. Besides the individual IPC gain, the eight cores now sit in a single large CCX (CPU core complex) rather than being split up into two 4-core CCX. The biggest gain from this is that all eight cores now share a single 16 MB L3 cache. This effectively doubles the addressable L3 cache over the previous generation. The iGPU is largely carried over from Renoir, with feature touch-ups to its display and media-acceleration components. The memory controller has been updated to support higher memory frequencies. It natively supports DDR4-3200 (compared to DDR4-2933 of Renoir), but, more importantly, handles higher memory overclocks. The only technological let-down is PCIe. AMD continues with Gen 3 PCIe, which is a big missed opportunity to add Gen 4 given Intel extends Gen 4 I/O to even its mid-tier Core i5 "Rocket Lake" parts.

The Zen 3 Microarchitecture

Since its 2017 debut, AMD has delivered a new iteration of its groundbreaking "Zen" CPU microarchitecture each year, each with IPC improvements. As we mentioned earlier, the new Zen 3 microarchitecture claims to offer a massive 19 percent IPC uplift over its predecessor, Zen 2. This is accomplished by improvements at both the micro and macro levels. We already detailed the macro (beyond the core) changes above. In this section, we talk about what's new inside each core. AMD mentioned updates to practically all key components of the core, including its front-end, fetch/decode, the integer and floating-point components, load-store, and the dedicated caches. Just to clarify, this component is unchanged compared to other Zen 3 CPUs without an IGP, like the Ryzen 9 5900X.


Modern processors execute multiple instructions in parallel to improve performance. Computer programs consist of huge amounts of "if ... then ... else" instructions, which slow down the processor because it has to evaluate the condition before picking a branch to execute. In order to overcome this limitation, the branch predictor was invented, a piece of circuitry that takes a guess on what's the more likely outcome of the condition check and just speculatively executes that branch's instructions. Of course, there's a chance that the prediction is wrong, in which case a performance penalty is incurred from undoing the executions that were already executed. With Zen 3, AMD uses an improved TAGE branch predictor, which is more accurate and recovers faster from mispredictions. They also changed the design to be "bubble free," which avoids inserting "wait for result" instructions into the instruction stream whenever a branch is encountered.

AMD generally increased operations per cycle; the front end now switches between the op and instruction caches faster. The 32 KB L1 instruction cache has been tweaked to offer better utilization due to efficient tagging and pre-fetching. Streamlining was done to the Op cache. Improvements to the branch predictor and front-end add up to nearly a quarter of the overall 19% generational IPC uplift.


The execution engine, or combination of the integer and floating-point execution units, is the main math muscle of the CPU core. The Zen 3 microarchitecture features improvements to both over Zen 2. Both the INT and FP issue queues (which feed work to the two engines) have been widened and the execution window enlarged. This ensures fewer units are idle in typical programs, which increases overall performance.


AMD worked to minimize latencies at every stage of the INT execution engine and enlarged its key structures, including the integer scheduler (96 entry vs. 92 on Zen 2), physical register file (192 vs. 180 on Zen 2), and 10 issues per cycle, up from 7 on Zen 2. Data picker bandwidth has been significantly increased despite the same number of ALUs. The floating-point engine features the same 256-bit FPUs, but just as with the INT engine, the FP engine has latency and bandwidth improvements across the board, a faster 4-cycle FMAC, and a larger scheduler. The INT and FP improvements contribute around a fifth of the 19% overall IPC uplift.


With the Zen 3 microarchitecture, AMD addressed many bottlenecks and "intelligence" issues with the Load/Store unit. The biggest has to be bandwidth. The entry store queue has been widened to 64 from 48 on Zen 2, and the L2 cache DTLB is 2K entries wide. The 32 KB L1 data cache has been made faster with lower latencies. Memory dependence detection has been improved. Much like the front end and scheduler, the load/store improvements contribute nearly a quarter of the 19% overall IPC uplift, meaning that by just optimizing the non-execution components of its core, AMD managed to pull off a vast 9% overall IPC uplift.

ISA and Security Changes

Each new microarchitecture heralds support for newer instruction sets and security hardening, and the same is the case with Zen 3; however, a notable absentee is AVX-512. Granted, Intel has adopted a less than perfect method of proliferating AVX-512 with certain instructions being exclusive to enterprise-segment microarchitectures and only a handful client-relevant instructions on its "Ice Lake" and "Tiger Lake" architectures, but there's no movement from AMD in this direction.

You still do get 256-bit instructions from within the AVX2 set. Also missing in action is something to rival Intel's DLBoost, which is essentially a software exposure of fixed-function hardware that accelerates matrix multiplication, in effect AI deep-learning neural net building and training. A lot of client applications, particularly image manipulation and video editing, are leveraging edge AI, and some investment from AMD on this would have been nice. That said, Zen 3 adds two new ISA instructions, MPK (memory protection keys) and AVX2 support for AES/APCLMulQD. AMD has been ahead of Intel with CPU core security vulnerability perception, and with Zen 3, AMD is introducing CET, or control-flow enforcement, which should provide hardening against ROP-type attacks.

Integrated Radeon Vega Graphics

The raison d'etre of the Ryzen 5000G series is its integrated graphics, something not found on other Ryzen 5000 series desktop processors. The AMD Cezanne silicon integrates an iGPU based on the same old Vega architecture, but with some improvements. Why AMD went with Vega and not at least RDNA1 is anyone's guess. The company is probably looking to conserve silicon real estate and thinks it can improve its performance to stay ahead of Rocket Lake, and its Gen12 Xe iGPU. The iGPU is mostly unchanged from the previous generation Renoir. It still only has up to 8 compute units (512 stream processors), 64 TMUs, and 8 ROPs and relies entirely on the system memory share. AMD updated a few things. These include a reworked power delivery system to the iGPU and reduced Vmin (minimum core voltage), a 350 MHz increase in engine clocks that are sustained better, and other improvements related to fabric and CU power. These power efficiency improvements convert to increased power budget, letting the iGPU sustain higher engine clocks better.

AMD X570 and B550 Chipsets

At launch, Ryzen 5000 Zen 3 processors should be compatible with all Socket AM4 motherboards based on AMD X570 and B550 chipsets, with a BIOS update that has the latest AGESA ComboPI 1.1.0.0 micro-code. The BIOS update must be installed before installing the Zen 3 CPU. Trying to boot the old BIOS with a Zen 3 will not work (we've tried). Luckily, most Socket AM4 motherboards feature some form of USB BIOS Flashback feature that lets you update the motherboard BIOS without having to install a processor or memory, which means you won't have to borrow an older processor just to update your motherboard's BIOS. Recent batches of AMD 500-series chipset motherboards should ship with Ryzen 5000 series support out of the box.

The AMD X570 chipset is a premium offering that enables PCI-Express gen 4.0 not just from the processor (i.e., the main x16 PEG slot and one M.2 NVMe slot), but also downstream PCIe lanes attached to the chipset. You get up to 16 PCIe gen 4 lanes from the chipset, which can be re-configured as SATA or USB3 ports by the motherboard designer. The B550 chipset lets you have one PCIe gen 4 main x16 slot and one M.2 NVMe slot, but all chipset-attached downstream lanes are PCIe gen 3. The B550 puts out eight downstream lanes. When paired with 5000G Cezanne processors, the downstream PCIe lanes of the X570 operate at Gen 3 speeds despite being capable of Gen 4.