If you have been looking to buy a new graphics card recently, you have probably stumbled upon these terms and wondered what they meant. It’s time to break it down and understand what’s what.
It’s natural to be confused, especially since Navi and RDNA have been wrongly used interchangeably. As this is a rather complex topic, we’ll cover the basics first.
First off, there is the Instruction Set Architecture or ISA, which can be thought of as an abstract model of a computer. It mainly defines the supported data types, registers, hardware support for managing main memory, and the input/output model of a family of implementations of the ISA. Put more simply, it’s basically an interface between hardware and software.
Microarchitecture is the way in which a given ISA is implemented in a specific processor. This means that Computer Architecture is the combination of Microarchitecture and ISA.
To make it more simple, RDNA and GCN are the codenames for both ISA and Microarchitecture for AMD GPUs, and Navi is the codename for the GPUs made with these architectures. Now that we got that out of the way, it’s time to get technical.
Table of ContentsShow
Graphics Core Next (GCN)
Let’s start with Graphics Core Next or GCN.
This is AMD’s codename for both a series of microarchitectures and an instruction set which was, back in 2012, part of a released product for the first time.
PCIe 3.0 standard was originally used but, as expected, when compared to today’s standards, these products aren’t nearly as power-efficient. Cards prior to GCN 4.0 were made on the 28nm manufacturing process, while their successors used the 14nm process.
Another clear pro of these cards is the fact that they supported GDDR5 memory; some later models even supported HBM2 and HBM memory. It’s worth noting that GCN is also used in graphics portions of AMD’s Accelerated Processing Units such as those in Playstation 4 and Xbox One APUs.
Radeon DNA (RDNA)
RDNA is a fairly new product – it is the direct successor to GCN and it was featured for the first time on the Radeon RX 5000 series that launched in 2019.
Naturally, it attempted to outdo GCN’s capabilities with its ability to support GDDR6 memory and PCIe 4.0 bus interface, which almost doubles the bandwidth offered by PCIe 3.0. Additionally, it features enhanced rendering pipeline, multilevel cache, operating primitive shaders, and a modernized display controller. It is also currently manufactured using the 7 nm process.
Navi refers to the GPU series built on the RDNA architecture with FinFET’s 7nm process. This is where it might get confusing but just think of RDNA as a broader term, as Navi GPUs have so far been exclusively found in the RX 5000 series and expanded to the RX 6000 series in 2020.
GCN vs RDNA
Rule of thumb in the technology world: newer equals better. It is no different in this case. This doesn’t mean that GCN isn’t good, but considering the increasing demands and technological advances, it falls short of RDNA’s results.
The new processing units of RDNA were redesigned to offer efficiency improvement and enhance the single-threaded performance when compared to the older GCN units.
RDNA’s IPC is 1, which shows a great upgrade from GCN’s 0.25. What this means is that RDNA can perform four times as many instructions per cycle, which is a crucial aspect in gaming.
The width of the wavefront of RDNA, 32, is also a big improvement compared to GCN’s 64. In other words, for GCN this meant that 64 threads were bundled in together for execution. This increases single-threaded performance by decreasing clock cycles, which comes in handy in games.
Something else that AMD has done in favor of RDNA was to expand the width of their SIMDs from 16 to 32, which means that the size of the wavefront now matches the size of the SIMD.
GCN put together the shader hardware into “compute units” which contained memory access, LDS, and scalar ALUs, and vector ALUs. One of these units contains 4 SIMD16s that share one path to memory.
In turn, RDNA has a “workgroup processor” that replaces the compute unit as the base shader computation unit with a 2 to 1 ratio. In practice, this allows RDNA to have more computing power and also more memory bandwidth, which can be steered at a single workgroup.
L1 cache grading is yet another innovation brought by RDNA. This hierarchy lowers the cache latency for every level, increases load bandwidth two-fold, and improves upon effective bandwidth. Basically, twice as much work is possible with the same amount of power.
RDNA vs Navi
There really isn’t much to be said about this, but as RDNA came out a clear winner in comparison to GCN, it’s only fair to mention Navi as well.
As previously stated, Navi refers mostly to the RX 5000 series’ use of RDNA, so these two terms are about as comparable as apples and oranges. Well, maybe apples and granny smith apples.
Once you’ve grasped all the confusing terms, it’s clear that RDNA is the most advanced technology out of the three. As such, it’s probably the safest choice at the moment.
However, it should be noted that AMD released RDNA 2 in late 2020. Additionally, RDNA 2 or “Big Navi” (talk about confusion) is part of Microsoft’s next-gen Xbox Series X and its Sony competitor Playstation 5.
So, being patient might pay off: you may be able to get your hands on an even newer option in the next few months.