If you have recently been looking to buy a fresh graphics card, you have probably stumbled across these terms and wondered what they denote. It’s time to break them down to understand what’s what.
It’s natural to be perplexed, especially as Navi and RDNA have erroneously been used interchangeably. As this is a rather complex topic, we will cover the basics first.
Firstly, there is the Instruction Set Architecture or ISA, which can be thought of as an abstract representation of a computer. It 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. In essence, it is an interface between hardware and computer software.
Microarchitecture is the way a given ISA is implemented in a specific processor. This means Computer Architecture is the combination of Microarchitecture and ISA.
To simplify, RDNA and GCN are the codenames for both ISA and Microarchitecture for AMD GPUs. Navi is the codename for the GPUs made with these architectures. With that out of the way, it’s time to get intricate.
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 an uncovered product for the first time.
PCIe 3.0 standard was originally used, but understandably, these products are far less power-efficient by today’s standards. Cards prior to GCN 4.0 were made on the 28nm manufacturing process, while their successors used the 14nm process.
Another clear benefit of these cards is the fact that they supported GDDR5 memory; some subsequent 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 comparatively recent item. It is the immediate heir of GCN and was showcased for the first occasion on the Radeon RX 5000 series that unveiled in 2019.
Naturally, it attempted to outdo GCN’s capabilities with its capacity to support GDDR6 memory and PCIe 4.0 bus interface, which nearly doubles the bandwidth provided by PCIe 3.0.
It also features an improved rendering pipeline, multilevel cache, operating primitive shaders, and a modernized display controller. It is currently manufactured using the 7nm process.
Navi
Navi refers to the GPU series constructed on the RDNA architecture with FinFET’s 7nm process. This is where things could become perplexing but think of RDNA as a more all-encompassing 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
The rule of thumb in the technology world is that newer equals superior. That 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 recent processing units of RDNA were modified to provide enhanced efficiency advancements and boost the performance of one task compared to the preceding GCN units.
RDNA’s IPC is 1, which is a substantial upgrade from GCN’s 0.25. This means that RDNA can perform four times as many instructions per cycle, which is a vital aspect of gaming.
The width of the wavefront of RDNA, 32, is also a considerable improvement compared to GCN’s 64. In other words, for GCN, this meant that 64 threads were bundled together for execution. This enhances single-threaded performance by decreasing clock cycles, which comes in beneficial in games.
Something else that AMD has done in favor of RDNA was to expand the scope of their SIMDs from 16 to 32, which means the size of the wavefront now matches the size of the SIMD.
GCN combined the shader hardware into “compute units,” which contained memory access, LDS, scalar ALUs, and vector ALUs. One of these units contains 4 SIMD16s that share one integrated path to memory.
In turn, RDNA has a “workgroup processor” that replaces the compute unit as the fundamental shader computation unit with a 2 to 1 ratio. In practice, this allows RDNA to have more processing power and also more memory bandwidth, which can be directed at a single crucial workgroup.
is yet another breakthrough brought by RDNA. This hierarchy decreases the cache latency at every level, boosts load bandwidth two-fold, and enhances effective bandwidth. Essentially, twice the amount of work is achievable with the identical amount of energy.
RDNA vs. Navi
There isn’t much to be said about this, but as RDNA came out as a clear winner in comparison to GCN, it’s only fair to mention Navi as well.
As previously mentioned, Navi refers mostly to the RX 5000 series’ use of RDNA, so these two terms are about as comparable as apples and oranges. Well, perhaps Braeburn apples and tart Granny Smith apples.
Conclusion
Once you understand these puzzling terms, it’s clear that RDNA is the most advanced technology of the three. As such, it’s likely the smartest choice at the moment.
It is vital to mention that AMD launched RDNA 2 in the later part of 2020. Furthermore, RDNA 2 or “Big Navi” (to add more confusion) is included in Microsoft’s next-generation Xbox Series X and its competitor from Sony, PlayStation 5.
For now, persistence might pay off; you should be able to get your hands on an even newer option in the forthcoming few months.