Rechercher dans ce blog

Saturday, February 27, 2021

Intel 8-Core Tiger Lake-H CPUs Claw Their Way Into Lenovo's Legion Laptops - Tom's Hardware

proc.indah.link

Intel's 11th-Gen eight-core Tiger Lake-H 45W processors for mobile devices are expected to land in the first quarter, and, judging by the latest retailer listings (via momomo_us), the 10nm chips shouldn't be far off.

Intel has launched several Tiger Lake chips that adhere to power limits under 35W. However, the chipmaker will have to roll out the 45W parts if it really wants to compete against AMD's core-heavy Ryzen 5000 (Cezanne) processors. Like all Tiger Lake offerings, the 45W processors are based on Intel's 10nm SuperFin (10SF) process node and wield Willow Cove cores and Xe LP graphics.

Besides the power limit increase, the 45W chips also bump Tiger Lake's maximum core count of up to eight cores, while current Tiger Lake processors on the market max out at four cores. However, the Tiger Lake-H 45W processors will allow Intel to contend with AMD in mobile high-end gaming and workstation devices.

Intel 11th Generation Tiger Lake-H 45W Specifications

Processor Cores / Threads Base / Boost Clocks (GHz)
Ryzen 9 5900HX 8 / 16 3.3 / 4.6
Core i9-11980HK* 8 / 16 ?
Ryzen 7 5800H 8 / 16 3.2 / 4.4
Core i7-11800H* 8 / 16 ?
Ryzen 5 5600H 6 / 12 3.3 / 4.2
Core i5-11400H* 6 / 12 ?

*Specifications are unconfirmed.

The four Tiger Lake-H processors from the Lenovo Legion listings cover only a few of the expected SKUs. Intel will likely flesh out the lineup with other configurations with slightly lower clock speeds to tend to different needs.

Barring any last-minute surprises, we expect the Core i9-11980HK to be the Tiger Lake-H flagship chip. In the same vein as its predecessors, the Core i9-11980HK should arrive with eight cores and 16 threads of processing power. The "K" suffix confirms that it will also have an unlocked multiplier for overclocking.

The Core i9-11980HK will go up against AMD's Ryzen 9 5900HX, which has the same core configuration and allows for overclocking. AMD claims the Ryzen 9 5900X delivers up to 14% more single-threaded performance than the Core i9-10900HK in Cinebench R20m as well as 37% and 21% higher scores in Passmark PT10 and Fire Strike Physics, respectively. Assuming that AMD's results are accurate, the Core i9-11980HK has a lot of catching up to do.

Intel 11th Generation Tiger Lake-H (Image credit: Provantage)

Meanwhile, the Core i7-11800H and Core i5-11400H should be equipped with eight cores and six cores, respectively. In the case of the Core i7-11800H, the operating clocks will be what separates it from the Core i9-11980HK or the rumored Core i9-11900H.

If we look at the Ryzen 5000 lineup, it's clear that Intel cooked up the Core i7-11800H and Core i5-11400H to confront the Ryzen 7 5800H and Ryzen 5 5600H, respectively. AMD didn't share any performance figures for the aforementioned SKUs, though.

Tiger Lake versus Ryzen 5000 will be an interesting fight for sure. Intel's Willow Cove microarchitecture faces AMD's Zen 3 microarchitecture, which has shown strong IPC uplifts over the previous microarchitecture. It's not just a battle of microarchitectures but also a struggle between process nodes, too. While AMD has tapped TSMC's proven 7nm process node, Intel's bringing its 10nm SuperFin to the rumble.

The Link Lonk


February 28, 2021 at 01:41AM
https://ift.tt/3b2gwLQ

Intel 8-Core Tiger Lake-H CPUs Claw Their Way Into Lenovo's Legion Laptops - Tom's Hardware

https://ift.tt/2YXg8Ic
Intel

The Intel Core i7-11700K is up for sale on German retailer's website for an eye-watering price - Notebookcheck.net

proc.indah.link

Please share our article, every link counts!

Anil Satyanarayana, 2021-02-25 (Update: 2021-02-26)

Anil Satyanarayana

I've been an avid PC gamer since the age of 8. My passion for gaming eventually pushed me towards general tech, and I've been a stereotypical 'nerd' ever since. I have a degree in mechanical engineering and have worked in the manufacturing industry. When I'm not writing news on Notebookcheck, you can find me playing or watching an intense match of DOTA 2

The Link Lonk


February 26, 2021 at 05:39AM
https://ift.tt/3bIocSx

The Intel Core i7-11700K is up for sale on German retailer's website for an eye-watering price - Notebookcheck.net

https://ift.tt/2YXg8Ic
Intel

All-AMD Dell G5 15 SE gaming laptop with Ryzen 5 4600H CPU and Radeon RX 5600M graphics now on sale for $685 USD - Notebookcheck.net

proc.indah.link

Please share our article, every link counts!

Allen Ngo, 2021-02-27 (Update: 2021-02-27)

Allen Ngo

After graduating with a B.S. in environmental hydrodynamics from the University of California, I studied reactor physics to become licensed by the U.S. NRC to operate nuclear reactors. There's a striking level of appreciation you gain for everyday consumer electronics after working with modern nuclear reactivity systems astonishingly powered by computers from the 80s. When I'm not managing day-to-day activities and US review articles on Notebookcheck, you can catch me following the eSports scene and the latest gaming news.

The Link Lonk


February 27, 2021 at 11:08AM
https://ift.tt/301qned

All-AMD Dell G5 15 SE gaming laptop with Ryzen 5 4600H CPU and Radeon RX 5600M graphics now on sale for $685 USD - Notebookcheck.net

https://ift.tt/2ZDueh5
AMD

EETimes - AMD, TSMC & Imec Show Their Chiplet Playbooks at ISSCC - - EE Times

proc.indah.link
[unable to retrieve full-text content]EETimes - AMD, TSMC & Imec Show Their Chiplet Playbooks at ISSCC -  EE Times The Link Lonk


February 27, 2021 at 03:29AM
https://ift.tt/3uzfm1Y

EETimes - AMD, TSMC & Imec Show Their Chiplet Playbooks at ISSCC - - EE Times

https://ift.tt/2ZDueh5
AMD

Intel DG2 Xe-HPG specs leak, 512-EU part with 16 GB GDDR6 VRAM can potentially challenge NVIDIA GeForce RTX 3070 and AMD Radeon RX 6800 - Notebookcheck.net

proc.indah.link

Intel recently introduced its first modern dGPU, the DG1 or Xe Max, for Tiger Lake laptops and select desktop configurations. During the previous Architecture Day event, Intel's graphics chief Raja Koduri said that the company will soon launch DG2 or Xe-HPG products aimed at mainstream gamers and content creators. While we've been hearing about Intel DG2 for quite some time now, a recent leak points to possible variants slated to launch later this year.

The info comes from several sources including @harukaze5719, @OneRaichu, and @hougetsu on Twitter. We've previously reported that Xe-HPG may feature up to 512 execution units (EUs) or 4,096 stream processors (SPs) and that Intel is exploring the possibility of scaling it up to 960 EUs as well. While we are still unsure about the 960-EU part, we are now getting to see some information about what all SKUs can be expected along with their VRAM capacities.

According to @hougetsu and @harukaze5719, who happened to decode @OneRaichu's cryptic tweet, Xe-HPG could be available in at least six variants. These include:

  • 512 EUs (4096 SPs) / 256 bit-bus / 8 or 16 GB VRAM
  • 384 EUs (3072 SPs) / 192 bit-bus / 6 or 12 GB VRAM
  • 256 EUs (2048 SPs) / 128 bit-bus / 4 or 8 GB VRAM
  • 192 EUs (1536 SPs) / 128 bit-bus / 4 GB VRAM
  • 128 EUs (1024 SPs) / 64 bit-bus / 4 GB VRAM
  • 96 EUs (768 SPs) / 64 bit-bus / 4 GB VRAM

The SKUs start from 96 EUs and go all the way up to 512 EUs. Intel already offers a 96-EU part with DG1, so we can expect the corresponding DG2 version to be faster with improved IPC and with GDDR6 RAM instead of LPDDR4x. The 256, 384, and 512-EU variants offer double VRAM choices as well with the highest being 16 GB GDDR6 on a 256-bit bus.

Going by available specs alone, RTX 3060 Ti/RTX 3070 levels of performance with the 512-EU variant is not improbable at the very least though the RX 6800 is also a potential competitor here in terms of available memory bandwidth.

While other details of Xe-HPG DG2 aren't yet available, we do know that the 384-EU SKU is likely to have a die area of 190 mm2. According to Intel, DG2 would be made fabbed in an external foundry, which we hear will be a TSMC 6 nm node. It is not yet known how these cards would be named, but the company may follow a nomenclature similar to NVIDIA and AMD.

Buy the NVIDIA GeForce RTX 3060 Ti on Best Buy

The Link Lonk


February 27, 2021 at 05:28PM
https://ift.tt/2ZVDX2R

Intel DG2 Xe-HPG specs leak, 512-EU part with 16 GB GDDR6 VRAM can potentially challenge NVIDIA GeForce RTX 3070 and AMD Radeon RX 6800 - Notebookcheck.net

https://ift.tt/2YXg8Ic
Intel

AMD Aldebaran Rumored To Be Arcturus’s Successor, Could Be Featured on Instinct MI200 GPU Accelerator - Wccftech

proc.indah.link

It looks like AMD is accelerating the production of its next-generation Instinct accelerator, the MI200, which is expected to feature an MCM GPU design. According to the latest information dump, not only is the codename for the GPU unveiled but also a range of new specifications.

AMD Instinct MI200 Accelerator Rumored To Be Codenamed Aldebaran, Will Succeed Arcturus With MCM GPU Design & HBM2E Memory

The AMD Instinct family, starting in 2020, is all CDNA architecture-based. The first generation CDNA flagship, the Instinct MI100, was internally codenamed Arcturus. It was a follow-up to Vega and the GPUs are named after giant stars. The successor to the Instinct MI100, the MI200, is also seemingly going to be named after a huge star and this time, it is expected to be known as Aldebaran.

AMD AGESA 1.2.0.1 BIOS Firmware Tested on MSI X570 & B550 Motherboards, Fixes L3 Cache Performance & Includes Improvements For Ryzen 5000 CPUs

In the latest Linux patch support (via Phoronix), the AMD Instinct MI200 could be known as Aldebaran which is a giant star located within the constellation of Taurus and has a solar radius of 44.13 or 75% more than Arcturus. The naming convention seems to suggest that Aldebaran will be twice as powerful as Arcturus since the numbers in the MI accelerator's naming convention represent the theoretical Flops performance. This is just speculation at this point but given that the accelerator is expected to feature an MCM GPU design, it might be real.

The patches also reveal that the AMD Instinct MI200 'Aldebaran' GPU will feature HBM2E memory support. The brand new memory standard was first used by NVIDIA's Ampere GA100 GPUs & will offer a nice boost over the standard HBM2 configuration used on the Arcturus-based MI100 GPU accelerator. HBM2E allows up to 16 GB memory capacity per stack so we can expect up to 64 GB HBM2E memory at blisteringly fast speeds for Aldebaran.

Other features listed include SDMA (System Direct Memory Access) support which will allow data transfers over PCIe and XGMI/Infinity Cache subsystems. It looks like AMD will incorporate its new Infinity Cache design on upcoming Instinct accelerators too so we are looking for a very advanced version of the Vega GPU.

AMD Unveils Radeon RX 6700 XT ‘Navi 22’ RDNA 2 Graphics Card on 3rd March, Will Tackle The RTX 3060 Ti

ARCTURUS ALDEBARAN
 .asic_family = CHIP_ARCTURUS,
.asic_name = “arcturus”,
.max_pasid_bits = 16,
.max_no_of_hqd = 24,
.doorbell_size = 8,
.ih_ring_entry_size = 8 * sizeof(uint32_t),
.event_interrupt_class = &event_interrupt_class_v9,
.num_of_watch_points = 4,
.mqd_size_aligned = MQD_SIZE_ALIGNED,
.supports_cwsr = true,
.needs_iommu_device = false,
.needs_pci_atomics = false,
.num_sdma_engines = 2,
.num_xgmi_sdma_engines = 6,
.num_sdma_queues_per_engine = 8,
.asic_family = CHIP_ALDEBARAN,
.asic_name = “aldebaran”,
.max_pasid_bits = 16,
.max_no_of_hqd = 24,
.doorbell_size = 8,
.ih_ring_entry_size = 8 * sizeof(uint32_t),
.event_interrupt_class = &event_interrupt_class_v9,
.num_of_watch_points = 4,
.mqd_size_aligned = MQD_SIZE_ALIGNED,
.supports_cwsr = true,
.needs_iommu_device = false,
.needs_pci_atomics = false,
.num_sdma_engines = 2,
.num_xgmi_sdma_engines = 3,
.num_sdma_queues_per_engine = 8,

There's also a hint at the MCM GPU design again for the AMD Instinct MI200 'Aldebaran GPU'. The patch states a new mode known as Performance Determinism in which the PMFW will maintain sustained performance level and can be enabled on a per-die basis. This would allow each GPU die to run this feature but a max graphics frequency needs to be specified so they don't exceed the power caps.

Do note that AMD's CDNA 2 GPU will be fabricated on a brand new process node & are confirmed to feature a 3rd Generation AMD Infinity architecture that extends to Exascale by allowing up to 8-Way coherent GPU connectivity.

AMD Radeon Instinct Accelerators 2020

Accelerator Name AMD Radeon Instinct MI6 AMD Radeon Instinct MI8 AMD Radeon Instinct MI25 AMD Radeon Instinct MI50 AMD Radeon Instinct MI60 AMD Instinct MI100 AMD Instinct MI100
GPU Architecture Polaris 10 Fiji XT Vega 10 Vega 20 Vega 20 Arcturus TBA
GPU Process Node 14nm FinFET 28nm 14nm FinFET 7nm FinFET 7nm FinFET 7nm FinFET Advanced Process Node
GPU Cores 2304 4096 4096 3840 4096 7680 7680 x 2 (MCM) ?
GPU Clock Speed 1237 MHz 1000 MHz 1500 MHz 1725 MHz 1800 MHz ~1500 MHz TBA
FP16 Compute 5.7 TFLOPs 8.2 TFLOPs 24.6 TFLOPs 26.5 TFLOPs 29.5 TFLOPs 185 TFLOPs TBA
FP32 Compute 5.7 TFLOPs 8.2 TFLOPs 12.3 TFLOPs 13.3 TFLOPs 14.7 TFLOPs 23.1 TFLOPs TBA
FP64 Compute 384 GFLOPs 512 GFLOPs 768 GFLOPs 6.6 TFLOPs 7.4 TFLOPs 11.5 TFLOPs TBA
VRAM 16 GB GDDR5 4 GB HBM1 16 GB HBM2 16 GB HBM2 32 GB HBM2 32 GB HBM2 TBA
Memory Clock 1750 MHz 500 MHz 945 MHz 1000 MHz 1000 MHz 1200 MHz TBA
Memory Bus 256-bit bus 4096-bit bus 2048-bit bus 4096-bit bus 4096-bit bus 4096-bit bus TBA
Memory Bandwidth 224 GB/s 512 GB/s 484 GB/s 1 TB/s 1 TB/s 1.23 TB/s TBA
Form Factor Single Slot, Full Length Dual Slot, Half Length Dual Slot, Full Length Dual Slot, Full Length Dual Slot, Full Length Dual Slot, Full Length OAM
Cooling Passive Cooling Passive Cooling Passive Cooling Passive Cooling Passive Cooling Passive Cooling Passive Cooling
TDP 150W 175W 300W 300W 300W 300W TBA

News Sources: Videocardz , Komachi , Coelacanth’s Dream

The Link Lonk


February 27, 2021 at 11:27AM
https://ift.tt/3aWppGr

AMD Aldebaran Rumored To Be Arcturus’s Successor, Could Be Featured on Instinct MI200 GPU Accelerator - Wccftech

https://ift.tt/2ZDueh5
AMD

AMD AGESA 1.2.0.1 BIOS Firmware Tested on MSI X570 & B550 Motherboards, Fixes L3 Cache Performance & Includes Improvements For Ryzen 5000 CPUs - Wccftech

proc.indah.link

AMD's AGESA 1.2.0.1 BIOS Firmware has been officially introduced and comes with a range of bug fixes and improvements for Ryzen 5000 Desktop CPUs. Board makers will be rolling out the BIOSes for each respective motherboard within their 500-series lineup.

AMD AGESA 1.2.0.1 BIOS Firmware Official - Adds Various Bug Fixes And Improvements For Ryzen 5000 Desktop CPUs, L3 Cache Performance Fix Demonstrated on MSI 500-Series Motherboards

According to AMD themselves, the first public BIOSes for Ryzen 5000 Desktop CPUs are rolling out now. AMD themselves confirm the following general fixes and improvements:

AMD Aldebaran Rumored To Be Arcturus’s Successor, Could Be Featured on Instinct MI200 GPU Accelerator

  • Fix: False SMART errors on Hynix NVMe
  • Fix: Intermittent SSD detection for M.2 SATA devices
  • Improve L3$ bandwidth in AIDA64
  • Improve stability if the user disables cores on 5600X/5800X with AMD Ryzen Master

In addition to the above-mentioned fixes/improvements, the AGESA 1.2.0.1 BIOS Firmware also addresses the L3 cache performance issue that users were facing when updating to 1.2.0.0 BIOS Firmware. For that purpose, a test setup with an AMD Ryzen 9 5950X CPU and an MSI MEG B550 Unify motherboard was used. The comparison was done with both the AGESA 1.2.0.0 and the new AGESA 1.2.0.1 firmware. You can see the comparison in L3 Cache performance below:

AMD Ryzen 9 5950X L3 Cache Performance on AGESA 1.2.0.0 BIOS Firmware:

AMD Ryzen 9 5950X L3 Cache Performance on AGESA 1.2.0.1 BIOS Firmware:

AMD Unveils Radeon RX 6700 XT ‘Navi 22’ RDNA 2 Graphics Card on 3rd March, Will Tackle The RTX 3060 Ti

As you can see, the AGESA 1.2.0.1 really does fix the L3 cache performance issues and the numbers are back to normal where they should be. Also, MSI has initially rolled out the AMD AGESA 1.2.0.1 Firmware on the following 500-series motherboards:

If you are running any of these motherboards, make sure to get the latest BIOS from MSI's to unlock the full potential of your AMD Ryzen 500 series desktop processor. We will keep you updated when other manufacturers release their respective BIOS Firmware based on the AMD AGESA 1.2.0.1 version.

The Link Lonk


February 27, 2021 at 04:42PM
https://ift.tt/3dSQbBI

AMD AGESA 1.2.0.1 BIOS Firmware Tested on MSI X570 & B550 Motherboards, Fixes L3 Cache Performance & Includes Improvements For Ryzen 5000 CPUs - Wccftech

https://ift.tt/2ZDueh5
AMD

Featured Post

Intel Falls on Latest Server Chip Delay; Rival AMD Gains - Yahoo Finance

proc.indah.link (Bloomberg) -- Intel Corp. fell after saying a new version of its Xeon server chip line will go into production in 2022, r...

Popular Posts