NVIDIA’s GeForce RTX 3080 series has been here for a few months. The RTX 3080 like its other siblings is an upgrade over its predecessor (RTX 2080 Super). NVIDIA has maxed out this GA102 silicon with 8704 CUDA cores across the cards 68 SMs. The 10GB of GDDR6X has also been given a upgrade from 15.5 Gbps to 19 Gbps. The RTX 3080 that we are taking a look at today comes from Zotac and it is their AMP Holo card. The AMP (not be the confused with the AMP Extreme) features a slight bump in its boost clock up to 1770 MHz (compared to 1710 MHz reference) a 13+3 power phase design, and a hefty cooling solution.
Features:
– 2nd Gen Ray Tracing Cores
– 3rd Gen Tensor Cores
– HoloBlack Design
– SPECTRA 2.0 RGB Lighting
– IceStorm 2.0 Advanced Cooling
– Active Fan Control with FREEZE Fan Stop
– Metal Frontplate and RGB LED Backplate
– FireStorm Utility
– VR Ready
The Zotac GeForce RTX 3080 Amp Holo is fitted with 10 Gigabyte GDDR6X memory, it runs at 19 Gbps (effective data rate) and that is a lot of bandwidth. The IO panel shows three DisplayPort 1.4, and one HDMI 2.1 connectors that will bring 8K 60 Hz HDR to a single HDMI cable. No more USB type-C Virtual Link connector. The card has three fans and uses the traditional power connector design, e.g. dual 8-pin. The card has a nice stylish shroud with underneath it a very beefy cooler. The dimensions of the card are 32 x 12 cm and it weighs close to 1.5 kg.
The back of the ZOTAC RTX 3080 Amp Holo shows a large backplate fitting to the card which helps to cool and stiffens the card so as to not flex around. Zotac did redesign the backplate with holo design.
Zotac has over-engineered cooling solutions of the tremendous levels of power consumption with Ampere. Interestingly, the three fans is new design with 11- blade with two fans blowing upward and one fan blowing inward.
HDMI 2.1* (up to 7680×[email protected])
*Ultra High Speed HDMI Cable is required to support 8K/60FPS or 4K/120FPS
Display connectivity options include three standard DisplayPort 1.4a and one HDMI 2.1. Interestingly, the USB-C port for VR headsets, which NVIDIA introduced on Turing Founders Editions, has been removed—guess it didn’t take off as planned.
The DisplayPort 1.4a outputs support Display Stream Compression (DSC) 1.2a, which lets you connect 4K displays at 120 Hz, and 8K displays at 60 Hz. Ampere can drive two 8K displays at 60 Hz with just one cable per display. Ampere is the first GPU to support HDMI 2.1, which increases bandwidth to 48 Gbps to support higher resolutions, like 4K144 and 8K30, with a single cable. With DSC, this goes up to 4K240 and 8K120.
NVIDIA’s new NVENC/NVDEC video engine is optimized to handle video tasks with minimal CPU load. The highlight here is added support for AV1 decode. Just like on Turing, you may also decode MPEG-2, VC1, VP8, VP9, H.264, and H.265 natively, at up to [email protected]. The encoder is identical to Turing; it supports H.264, H.265 and lossless at up to [email protected].
[Left: Zotac RTX 3080 Amp Holo]
[Right Zotac RTX 2080 Amp Extreme]
The Zotac RTX3080 Amp Holo look smaller.
The card takes in two 8-pin PCIe power connectors. This setup is rated for 375 W and does not support SLI.
Disassembling the Zotac GeForce RTX 3080 AMP Holo aren’t straightforward and there are three layer to dismantle. The cooler features seven heatpipes and three 90 mm fans.
Once the main heatsink is removed, a metal frame that provides rigidity for the card becomes visible. It also helps cool the VRM circuitry.
There are 3 part to dismantle to access PCB.
The GA102-200 GPU, GPU and memory power phases, and GDDR6X memory from Micron labeled D8BGW. The GPU gets 13 phases managed by a duo uPI uP9511R multi-phase controllers. The memory is then managed by uP9511R over three phases. We see six SPCAPs and no MLCCs configured.
Three phase memory VRM is managed by a third uP9511S controller.
One uS5650P is a GPU power monitor controllers.
GStek GS9238 is a dynamic power management controllers, features include wide input voltage
range, high efficiency and fast dynamic response power save mode, which can save battery power supply by decreasing frequency when load current falls down below preset critical current point.
The Holtek HT32F52342 is a high performance, low power consumption 32-bit microcontrollers based around an ARM Cortex-M0+ processor core. It’s control RGB lighting for the card
On the back of the PCB spot a pair of uPI uP9511S multi-phase controllers pull a 13-phase GPU VRM. One uS5650P is a GPU power monitor controllers.
Zotac is using DrMOS components throughout the VRM.
The GDDR6X memory chips are made by Micron and carry the model number D8BWW. They are specified to run at 1188 MHz (19 Gbps GDDR6X effective).
GDDR6X doubles the data rate once again over GDDR6. It no longer transmits one bit of information by setting the voltage to either “on” or “off”, but instead sends two bits of information at the same time by using four different voltage levels.
GDDR6X – The Next Evolution in Graphics Memory, Designed Exclusively For NVIDIA’s GeForce RTX 30 Series Graphics Cards
The Micron GDDR6X memory brings a lot of new stuff to the table. It is faster, doubles the I/O data rate, and is the first to implement PAM4 multi-level signaling in memory dies. With the Geforce RTX 3090 class products, Micron’s GDDR6X memory achieves a bandwidth of up to 1 TB/s which is used to power the next-generation gaming experiences at high-fidelity resolutions such as 8K.
The new GDDR6X SGRAM:
- Doubles the data rate of SGRAM at a lower power per transaction while enabling breaking of the 1 Terabyte per second (TB/s) system memory bandwidth boundary for graphics card applications;
- Is the first discrete graphics memory device that employs PAM4 encoded signaling between the processor and the DRAM, using four voltage levels to encode and transfer two bits of data per interface clock.
- Can be designed and operated stably at high speeds, and built-in mass-production.
As mentioned, GDDR6X features the brand new PAM4 multilevel signaling techniques which helps transfer data much faster, doubles the I/O rate, pushing the capability of each memory dies from 64 GB/s to 84 GB/s. The Micron GDDR6X memory dies are also the only graphics DRAM that can be mass-produced while feature PAM4 signaling.
What is interesting is that Micron quotes that its GDDR6X memory can hit speeds of up to 21 Gbps whereas we have only got to see 19.5 Gbps in action on the GeForce RTX 3090. It is likely that AIBs could utilize higher binned dies as they are available. Micron also confirms that they plan to offer speeds higher than 21 GB/s moving in 2021 but we will have to wait and see whether any cards will utilize them.
It’s not just faster speeds but Micron’s GDDR6X provides higher bandwidth while sipping in 15% lower power per transferred bit compared to the previous generation GDDR6 memory.
Micron GDDR6X Memory
Feature | GDDR5 | GDDR5X | GDDR6 | GDDR6X |
---|---|---|---|---|
Density | From 512Mb to 8Gb | 8Gb | 8Gb, 16Gb | 8Gb, 16Gb |
VDD and VDDQ | Either 1.5V or 1.35V | 1.35V | Either 1.35V or 1.25V | Either 1.35V or 1.25V |
VPP | N/A | 1.8V | 1.8V | 1.8V |
Data rates | Up to 8 Gb/s | Up to 12Gb/s | Up to 16 Gb/s | 19 Gb/s, 21 Gb/s, >21 Gb/s |
Channel count | 1 | 1 | 2 | 2 |
Access granularity | 32 bytes | 64 bytes 2x 32 bytes in pseudo 32B mode |
2 ch x 32 bytes | 2 ch x 32 bytes |
Burst length | 8 | 16 / 8 | 16 | 8 in PAM4 mode 16 in RDQS mode |
Signaling | POD15/POD135 | POD135 | POD135/POD125 | PAM4 POD135/POD125 |
Package | BGA-170 14mm x 12mm 0.8mm ball pitch |
BGA-190 14mm x 12mm 0.65mm ball pitch |
BGA-180 14mm x 12mm 0.75mm ball pitch |
BGA-180 14mm x 12mm 0.75mm ball pitch |
I/O width | x32/x16 | x32/x16 | 2 ch x16/x8 | 2 ch x16/x8 |
Signal count | 61 – 40 DQ, DBI, EDC – 15 CA – 6 CK, WCK |
61 – 40 DQ, DBI, EDC – 15 CA – 6 CK, WCK |
70 or 74 – 40 DQ, DBI, EDC – 24 CA – 6 or 10 CK, WCK |
70 or 74 – 40 DQ, DBI, EDC – 24 CA – 6 or 10 CK, WCK |
PLL, DCC | PLL | PLL | PLL, DCC | DCC |
CRC | CRC-8 | CRC-8 | 2x CRC-8 | 2x CRC-8 |
VREFD | External or internal per 2 bytes | Internal per byte | Internal per pin | Internal per pin 3 sub-receivers per pin |
Equalization | N/A | RX/TX | RX/TX | RX/TX |
VREFC | External | External or Internal | External or Internal | External or Internal |
Self refresh (SRF) | Yes Temp. Controlled SRF |
Yes Temp. Controlled SRF Hibernate SRF |
Yes Temp. Controlled SRF Hibernate SRF VDDQ-off |
Yes Temp. Controlled SRF Hibernate SRF VDDQ-off |
Scan | SEN | IEEE 1149.1 (JTAG) | IEEE 1149.1 (JTAG) | IEEE 1149.1 (JTAG) |
However, the Amp Holo RGB lighting do not cover bottom area.
How We Tested Zotac’s RTX3080 AMP HOLO
GeForce RTX 3080 is the second highest end graphics card in Nvidia’s Ampere-based segment. As such, our graphics workstation, based on an ASRock B550 Taichi motherboard and AMD 5600X 6 cores processor. The ram we will be using is G.Skill’s F4-3600C16D- 16GTZNC memory kit. ADATA XPG GAMMIX S50 Lite 1TB M.2 NVMe SSD is used as well to run with benchmark.
We will be using latest Nvidia DCH driver 461.09 and Windows 10 Professional Build 20H2 19042.746.
GPUZ: RTX 3080 AMP Holo & RTX 2080 AMP Extreme:
Unigine Benchmark
Benchmark is a GPU-intensive benchmark that hammers graphics cards to the limits. This powerful tool can be effectively used to determine the stability of a GPU under extremely stressful conditions, as well as check the cooling system’s potential under maximum heat output.
Super Position 4K | Super Position 8K | |
RTX2080 AMP Extreme | 8987 | 3867 |
RTX3080 AMP Holo | 13661 | 6072 |
3Dmark Advanced Edition
3DMark includes everything you need to benchmark your PC and mobile devices in one app. Whether you’re gaming on a smartphone, tablet, notebook, or a desktop gaming PC, 3DMark includes a benchmark designed specifically for your hardware.
Time Spy | Fire Strike Ultra | Port Poyal | Direct X Raytracing | VRS Tier 1 | VRS Tier 2 | Nvidia DLSS | |
RTX2080 AMP Extreme | 10517 | 6677 | 6653 | 2093 | 99761 | 12838 | 7315 |
RTX3080 AMP Holo | 14563 | 10455 | 6072 | 4664 | 150363 | 19621 | 11516 |