AMD this Monday in a blog post demystified the boosting algorithm and thermal management of its new Radeon RX 5700 series "Navi" graphics cards. These cards are beginning to be available in custom-designs by AMD's board partners, but were only available as reference-design cards for over a month since their 7th July launch. The thermal management of these cards spooked many early adopters accustomed to seeing temperatures below 85 °C on competing NVIDIA graphics cards, with the Radeon RX 5700 XT posting GPU "hotspot" temperatures well above 100 °C, regularly hitting 110 °C, and sometimes even touching 113 °C with stress-testing application such as Furmark. In its blog post, AMD stated that 110 °C hotspot temperatures under "typical gaming usage" are "expected and within spec."

AMD also elaborated on what constitutes "GPU Hotspot" aka "junction temperature." Apparently, the "Navi 10" GPU is peppered with an array of temperature sensors spread across the die at different physical locations. The maximum temperature reported by any of those sensors becomes the Hotspot. In that sense, Hotspot isn't a fixed location in the GPU. Legacy "GPU temperature" measurements on past generations of AMD GPUs relied on a thermal diode at a fixed location on the GPU die which AMD predicted would become the hottest under load. Over the generations, and starting with "Polaris" and "Vega," AMD leaned toward an approach of picking the hottest temperature value from a network of diodes spread across the GPU, and reporting it as the Hotspot.

Here's the first picture of a possible custom-design Radeon RX 5700-series graphics card by XFX. The company could leverage this common board design to develop both Radeon RX 5700 XT and RX 5700 products. The design involves a large custom-design cooling solution that uses an aluminium fin-stack heatsink that's ventilated by a pair of large 100 mm fans. It's likely that the card will offer idle fan-stop looking at the size of the heatsink and the idle power-draw of the "Navi 10" silicon. The card could also feature some RGB LED embellishments. At this point it's not known if XFX has designed its own custom-design PCB for the "Navi 10," or whether it's using a reference- or close-to-reference PCB design. AMD's add-in board partners are expected to launch custom-design RX 5700-series products in August.

AMD is developing a larger GPU based on its new "Navi" architecture to power a new high-end graphics card family, likely the Radeon RX 5800 series. The codename "Navi 12" is doing rounds on social media through familiar accounts that have high credibility with pre-launch news and rumors. The "Navi 10" silicon was designed to compete with NVIDIA's "TU106," as its "XT" and "Pro" variants outperform NVIDIA's original RTX 2060 and RTX 2070, forcing it to develop the RTX 20 Super series, by moving up specifications a notch.

Refreshing its $500 price-point was particularly costly for NVIDIA, as it was forced to tap into the 13.6 billion-transistor "TU104" silicon to carve out the RTX 2070 Super; while for the RTX 2060 Super, it had to spend 33 percent more on the memory chips. With the "Navi 12" silicon, AMD is probably looking to take a swing at NVIDIA's "TU104" silicon, which has been maxed out by the RTX 2080 Super, disrupting the company's $500-700 lineup once again, with its XT and Pro variants. There's also a remote possibility of "Navi 12" being an even bigger chip, targeting the "TU102."

Two of the often overlooked components of a new graphics architecture are the I/O and multimedia capabilities. With its Radeon RX 5700-series "Navi 10" graphics processor, AMD gave the two their first major update in over two years, with the new Radeon Display Engine, and Radeon Multimedia Engine. The Display Engine is a hardware component that handles the graphics card's physical display I/O. The Radeon Multimedia Engine is a set of fixed-function hardware that provides CODEC-specific acceleration to offload your CPU.

The Navi Radeon Display Engine features an updated DisplayPort 1.4 HDR implementation that's capable of handling 8K displays at 60 Hz with a single cable. It can also handle 4K UHD at 240 Hz with a single cable. These also include HDR and 10-bit color. It achieves this by implementing DSC 1.2a (Display Stream Compression). The display controller also supports 30 bpp internal color-depth. The HDMI implementation remains HDMI 2.0. The multi-plane overlay protocol (MPO) implementation now supports a low-power mode. This should, in theory, reduce the GPU's power draw when idling or playing back video.

AMD "Navi 10" is a very different GPU from the "Vega 10," or indeed the "Polaris 10." The GPU sees the introduction of the new RDNA graphics architecture, which is the first big graphics architecture change on an AMD GPU in nearly a decade. AMD had in 2011 released its Graphics CoreNext (GCN) architecture, and successive generations of GPUs since then, brought generational improvements to GCN, all the way up to "Vega." At the heart of RDNA is its brand new Compute Unit (CU), which AMD redesigned to increase IPC, or single-thread performance.

Before diving deeper, it's important to confirm two key specifications of the "Navi 10" GPU. The ROP count of the silicon is 64, double that of the "Polaris 10" silicon, and same as "Vega 10." The silicon has sixteen render-backends (RBs), these are quad-pumped, which work out to an ROP count of 64. AMD also confirmed that the chip has 160 TMUs. These TMUs are redesigned to feature 64-bit bi-linear filtering. The Radeon RX 5700 XT maxes out the silicon, while the RX 5700 disables four RDNA CUs, working out to 144 TMUs. The ROP count on the RX 5700 is unchanged at 64.

It's been a very busy May-June for AMD as the company pushes out its major client-segment product lines spread across Computex 2019, and E3 2019. At Computex, the company focused on its 3rd generation Ryzen "Zen 2" desktop processors, and led its partners to show us a galaxy of new motherboards based on the AMD X570 chipset. It turns out that the company was saving a handful processor SKUs focused on gamers for E3.

The second important product launch of course is Radeon RX 5700 series, based on AMD's new "Navi 10" silicon on which its new RDNA graphics architecture debuts. With its AIB (add-in board) partners expected to be allowed to make custom-design cards, and based on what little nuggets of information AMD put out, "Navi" promises to stir up a key performance-segment price-band that's currently held by NVIDIA's GeForce RTX 2070 and RTX 2060. The AMD keynote will see the company CEO Dr. Lisa Su and her top execs take centerstage to make some big announcements. With E3 being a purely entertainment / client-segment forum, the AMD keynote promises not bore with tiresome topics such as AI, self-driving cars, etc.2:30 PM PDT: Ahead of its keynote, AMD posted a teaser video of its new RDNA graphics architecture on YouTube.

Ahead of its official reveal at AMD's E3 2019 keynote scheduled for 3 PM (Pacific) later today, VideoCardz scored a key slide that spills the beans on AMD's next performance-segment graphics card, the Radeon RX 5700 XT. This card is based on the 7 nm "Navi 10" silicon, and is its "XT" (maxed-out) SKU. Its reference-design board design in the slide reveals a return to a lateral-blower type cooling solution that now has a prettier cooler shroud with silver ridges and Radeon logos on two sides, one of which is illuminated, with a possible RGB LED accent that runs along the top of the card.

The specifications revealed point to 40 compute units. Unless AMD changed the stream processor count per CU with the RDNA architecture from 64, this works out to 2,560 stream processors. When combined with a stellar engine boost frequency of up to 1905 MHz, the GPU has a compute throughput of 9.75 TFLOP/s, which is 37 percent higher than that of the RX 590, but 27 percent lower than the Radeon VII, and roughly similar to the RX Vega 56. The RX 5700 XT is armed with 8 GB of GDDR6 memory, although the slide won't mention memory clock-speeds or bandwidth. AMD may disclose pricing and availability in its keynote address later today.

AMD's 7 nm "Navi 10" silicon may finally address two architectural shortcomings of its performance-segment GPUs, memory bandwidth, and render-backends (deficiency thereof). The GPU almost certainly features a 256-bit GDDR6 memory interface, bringing about a 50-75 percent increase in memory bandwidth over "Polaris 30." According to a sketch of the GPU's SIMD schematic put out by KOMACHI Ensaka, Navi's main number crunching machinery is spread across eight shader engines, each with five compute units (CUs).

Five CUs spread across eight shader engines, assuming each CU continues to pack 64 stream processors, works out to 2,560 stream processors on the silicon. This arrangement is in stark contrast to the "Hawaii" silicon from 2013, which crammed 10 CUs per shader engine across four shader engines to achieve the same 2,560 SP count on the Radeon R9 290. The "Fiji" silicon that followed "Hawaii" stuck to the 4-shader engine arrangement. Interestingly, both these chips featured four render-backends per shader engine, working out to 64 ROPs. AMD's decision to go with 8 shader engines raises hopes for the company doubling ROP counts over "Polaris," to 64, by packing two render backends per shader engine. AMD unveils Navi in its May 27 Computex keynote, followed by a possible early-July launch.

Rumors of AMD's next-generation performance-segment graphics card are gaining traction following a leak of what is possibly its PCB. Tweaktown put out a boatload of information of the so-called Radeon RX 3080 XT graphics card bound for an 2019 E3 launch, shortly after a Computex unveiling. Based on the 7 nm "Navi 10" GPU, the RX 3080 XT will feature 56 compute units based on the faster "Navi" architecture (3,584 stream processors), and 8 GB of GDDR6 memory across a 256-bit wide memory bus.

The source puts out two very sensational claims: one, that the RX 3080 XT performs competitively with NVIDIA's $499 GeForce RTX 2070; and two, that AMD could start a price-war against NVIDIA by aggressively pricing the card around the $330 mark, or about two-thirds the price of the RTX 2070. Even if either if not both hold true, AMD will fire up the performance-segment once again, forcing NVIDIA to revisit the RTX 2070 and RTX 2060.