|
Tuesday, February 18, 2014
Nvidia Announces The GeForce GTX 750, GTX 750 Ti And GTX Titan
Black GPUs
|
|
You are sending an email that contains the article
and a private message for your recipient(s). |
Your Name: |
|
Your e-mail: |
* Required! |
Recipient (e-mail): |
* |
Subject: |
* |
Introductory Message: |
|
HTML/Text
(Photo: Yes/No) |
(At the moment, only Text is allowed...)
|
|
|
Message Text: |
Nvidia today took the wraps off the new GeForce GTX 750 and GTX 750 Ti GPUs, both based on its first-generation "Maxwell" technology. The company also unveiled the successor of the GTX 780Ti, the Geforce GTC Titan Black.
Both the GeForce GTX 750 and the GTX 750 Ti are based on the
Maxwell GM107 GPU, which was made using TSMC's 28nm HP node.
Nvidia's Maxwell is a Direct3D 11.0 compliant design,
supporting the base 11.0 functionality along with many of the
features required for Direct3D 11.1 and 11.2.
I/O functionality is identical to Kepler, with 4 display
controllers backing NVIDIA's capabilities. HDMI 1.4 and
DisplayPort 1.2 functionality join the usual DVI support.
With Maxwell, NVIDIA's video encoder NVENC, has received an
performance boost. NVIDIA says that Maxwell's NVENC should be
1.5x-2x faster than Kepler's NVENC.
Decoding is also receiving a bit of a lift. Maxwell's VP video
decode block won't feature full H.265 (HEVC) support, but it
will offer partial hardware acceleration, relying on software
and hardware to decode H.265. Nvidia says that decoding is
getting a 8x-10x performance boost due to the implementation
of a local decoder cache and an increase in memory efficiency
for video decoding.
The company has also improved the density of the new designs
with Maxwell. Denser designs allow for NVIDIA to offer similar
performance as larger Kepler GPUs with a smaller Maxwell GPU.
With GM107 in being a 128-bit design that would need to
compete with the likes of the 192-bit GK106, NVIDIA has
increased the amount of L2 cache they use, from 256KB in GK107
to 2MB on GM107.
But most importantly, with Maxwell NVIDIA is almost solely
focused on improving energy efficiency and performance per
watt.
Nvidia says a GeForce GTX 750 Ti running at 1080p resolution
doubles the performance and uses half the power of the GTX 550
Ti, which was built with the Fermi architecture.
The GTX 750 Ti also approximates the performance of the
GeForce GTX 480 -- a $499 flagship product also based on the
Fermi architecture -- while consuming only one-fourth the
power, or 60 watts.
The GTX 750 Ti and 750 GPUs also include support for NVIDIA's
GameWorks program and gaming technologies, including:
- ShadowPlay, which lets gamers capture and share their gaming
experiences on Twitch and other online sites,
- G-SYNC display technology, for stutter-free gaming visuals,
and
- GameStream, which allows gamers to stream their favorite PC
games to NVIDIA SHIELD for high-performance gaming on the go.
In terms of specs, the GeForce GTX 750 Ti packs a complete
GM107 implementation, comprising 5 SMMs, 640 CUDA cores, 16
ROPs, and 40 texture units, and fed by 2MB of L2 cache.
GTX 750 Ti?s GM107 GPU is paired with 2GB of GDDR5, on a
128-bit bus.
The GTX 750 Ti GPU's small physical design -- at 5.7-inches
long -- doesn't require an internal power connector.
When it comes to clockspeeds NVIDIA is putting the GTX 750
Ti's core clock at 1020MHz with a boost clock of 1085MHz. The
memory will be clocked at 5.4GHz, which on a 128-bit bus is
enough to provide 86.4GB/sec of memory bandwidth.
NVIDIA wants to leverage GM107 and the GTX 750 series to
capture this market for HTPC use and OEM system upgrades
alike. The GTX 750 is based on a cut-down GM107 GPU, utilizing
just 4 of GM107?s 5 SMMs. This reduces the CUDA core count to
512 and the number of texture units to 32. GPU clockspeeds are
identical to GTX 750 Ti while the memory subsystem is further
reduced to 1GB of GDDR5 running at 5GHz.
NVIDIA GPU Specification |
|
GTX 660 |
GTX 750 Ti |
GTX 750 |
GTX 650 |
CUDA Cores |
960 |
640 |
512 |
384 |
Texture Units |
80 |
40 |
32 |
32 |
ROPs |
24 |
16 |
16 |
16 |
Core Clock |
980MHz |
1020MHz |
1020MHz |
1058MHz |
Boost Clock |
1033MHz |
1085MHz |
1085MHz |
N/A |
Memory Clock |
6GHz GDDR5 |
5.4GHz GDDR5 |
5GHz GDDR5 |
5GHz GDDR5 |
Memory Bus Width |
192-bit |
128-bit |
128-bit |
128-bit |
VRAM |
2GB |
2GB |
1GB |
1GB |
FP64 |
1/24 |
1/32 |
1/32 |
1/24 |
TDP |
140W |
60W |
55W |
64W |
Transistor Count |
2.54B |
1.87B |
1.87B |
1.3B |
Manufacturing Process |
TSMC 28nm |
TSMC 28nm |
TSMC 28nm |
TSMC 28nm |
Architecture |
Kepler |
Maxwell |
Maxwell |
Kepler |
GPU |
GK106 |
GM107 |
GM107 |
GK107 |
Price |
$229 |
$149 |
$119 |
$109 |
The NVIDIA GeForce GTX 750 Ti and GTX 750 GPUs are now
available from Nvidia's add-in card suppliers, including ASUS,
Colorful, EVGA, Gainward, Galaxy, Gigabyte, Innovision 3D,
MSI, Palit, PNY and Zotac. Pricing is expected to start at
$119 for the GTX 750, $139 for the 1GB GTX 750 Ti and $149 for
the 2GB GTX 750 Ti.
The GeForce GTX 750 Ti and GTX 750 GPUs will also be sold in
fully configured systems from U.S.-based system builders.
NVIDIA is placing both the GTX 750 Ti and GTX 750 between the
GK106 flagship GTX 660 and the GK107 flagship GTX 650. The GTX
750 Ti will replace the GTX 650 Ti Boost, and GTX 750 is
expected to retire GTX 650 Ti.
AMD's competition for the GTX 750 series will be the Radeon R7
265, and the recently price dropped Radeon R7 260X, which are
set to go for $149 and $119 respectively.
According to the first reviews for the cards that have
appeared online, the the GTX 750 Ti is nearly 2x as fast as
the GTX 650, and nearly 3x faster than the GT 640.
However, Radeon R7 265 holds a 15-20% lead over GTX 750 Ti.
Similarly, Radeon R7 260X averages a 10% lead over GTX 750,
and it does so while having 2GB of VRAM to GTX 750's 1GB.
NVIDIA's GeForce GTX Titan Black
NVIDIA's GeForce GTX Titan Black is a full GK110 implementation, just like the GTX 780 Ti, and packs 6GB of GDDR5. Titan Black improves on its predecessor by also using the full GK 110 die, one that calls for 2,880 shaders and 240 texture-units housed in 15 SMXs. Titan Black delivers a 5.1 Teraflops of computing performance per card
Core frequency sees a nice hike over first-generation Titan, now running at a peak 980MHz instead of 876MHz.The memory runs at a full 7GHz data rate just like the 780 Ti.
The GK110 core and boost clocks are up by 1.6% and 5.6%
compared to the 780 Ti, respectively.
And compared to the original Titan, you should expect a 14% to a 20% increase in performance on compute bound workloads or a 17% increase on memory bandwidth bound workloads. Gaming performance should be equal to the 780 Ti.
|
GTX Titan Black |
GTX 780 Ti |
GTX Titan |
GTX 780 |
Stream Processors |
2880 |
2880 |
2688 |
2304 |
Texture Units |
240 |
240 |
224 |
192 |
ROPs |
48 |
48 |
48 |
48 |
Core Clock |
889 MHz |
875 MHz |
837 MHz |
863 MHz |
Boost Clock |
980 MHz |
928 MHz |
876 MHz |
900 MHz |
Memory Clock |
7GHz GDDR5 |
7GHz GDDR5 |
6GHz GDDR5 |
6GHz GDDR5 |
Memory Bus Width |
384-bit |
384-bit |
384-bit |
384-bit |
VRAM |
6GB |
3GB |
6GB |
3GB |
FP64 |
1/3 FP32 |
1/24 FP32 |
1/3 FP32 |
1/24 FP32 |
TDP |
250W |
250W |
250W |
250W |
Transistor Count |
7.1B |
7.1B |
7.1B |
7.1B |
Manufacturing Process |
TSMC 28nm |
TSMC 28nm |
TSMC 28nm |
TSMC 28nm |
Price |
$999 |
$699 |
$999 |
$649 |
Each TITAN BLACK also supports up to four displays per card - two DVI, one HDMI and one DisplayPort.
Availability is expected to be limited on the GeForce GTX
Titan Black, with cards to retail for $999.
|
|
|
|
|