[mascotzel]

Originally Posted by Mandea

4750 nu a aparut, aia o sa fie un 4770 mai slab. dar nu sunt unul si acelasi lucru. bine, asa era vb, poate nu mai apare. oricum, 4770 merita din plin.

asculta ce zice eu
acel 4750 din review e actualul 4770,cu un GPU clock mai mare ca sa taie si mai tare din Nvidia ( "750 "early engineering", deci nu avea specificatiile finalizate,asa cum se deduce din text)

Meet the Radeon HD 4750

Okay then, you fine men and women would of course like to learn everything about this little silicon called RV740. So, we'll try to get you as much information as we can gather. But obviously we have only very limited information at hand.

A good way to explain a product is to always explain what it is not.

RV740 is not a high-end graphics card. In fact if the board partner that submitted this card is correct, it's pricing would be below 99 USD. That would make it fare into the budget segment. But it's not a budget product either.

The chip will be the successor to the RV730 (Radeon HD 4650/4670), although that product will still remain in the market for a while, we think, AMD can redefine the budget to middle class product line-up. See, performance of the strongest RV740 based product will move upwards in-between HD 4830 and HD 4850 performance.

It is a very spiffy card when it comes to performance (for the money of course). Here's what we know. RV740 has 640 shaders (stream processors). The core frequency for the early engineering sample card we tested is 650 MHz.

RV740 is based off a 40nm production node and is equipped with 128-bit memory. Now before your go "aaahw, we lost half the framebuffer bandwidth due to 128-bit memory", here's the thing. The RV740 is equipped with GDDR5 memory. This GDDR5 memory is running at 800 MHz, that would boil down to 3200 MHz, 3.2 Gbps effective... that's just over 50 GB/sec of bandwidth depending on the final memory configuration.

Now if you cut down the memory bus in half to 128-bit you lose half the bandwidth, ATI compensates for that by doubling it up again with GDDR5 memory. It's a bit of a tradeoff here and there. See, 128-bit memory is fairly cheap to use and does return a heap of framebuffer bandwidth thanks to the higher frequency memory. Also I can imagine a simpler design in the PCB such as using less wires and thus a cheaper design. On the flip side, slower memory latency timings. But granted, this choice makes a lot of sense, as the results will show.

Now I've fired off some math at the most generic denominators and when we place things in a chart, you'll gain some perspective of product differences.

The RV740 houses 640 stream processors, 32 texture memory units (TMUs) and 16 render output units (abbreviated as ROPs). As stated, It features a 128-bit wide bus using GDDR5 memory, bumping up bandwidth that rivals equally clocked GDDR3 with double the bus width. Very interesting.

Meet the Radeon HD 4770

So then, to understand what is powering up that Radeon HD 4770 first we need to learn what's inside it. The basis of the card is in essence the graphics processor and it's video memory, slapped onto a PCB with crystals, PLLs, voltage regulators, resistors, capacitors etc etc.

The GPU used on this card has the following codename -- RV740.

RV740 is the replacement of the RV730 (Radeon HD 4650/4670), that product line will still remain in the market for a while, yet we think RV740 in time will replace it completely as this series is just too strong. Why you ask? Well, the RV740 is really a disciple of RV770, yes indeed... the Radeon HD 4850/4870.

By making this move, AMD slash ATI will redefine the budget to middle class product line-up as performance of the strongest RV740 based product will move upwards in-between the HD 4830 and horribly close to HD 4850 performance.

It is a very spiffy card when it comes to performance (for the money of course). Radeon HD 4770 has 640 shaders (stream processors). The final core frequency for the card we tested is 750 MHz.

RV740 is based off a 40nm production node and is equipped with 128-bit memory. Now before your go "aaahw, we lost half the framebuffer bandwidth due to 128-bit memory", here's the thing. The RV740 is equipped with GDDR5 memory. This GDDR5 memory is running at 800 MHz, that boils down to 3200 MHz, 3.2 Gbps effective, and that's just over 50 GB/sec of bandwidth on the final memory configuration.

Now if you cut down the memory bus in half to 128-bit you lose half the bandwidth, ATI compensates for that by doubling it up again with GDDR5 memory. It's a bit of a tradeoff here and there. See, 128-bit memory is fairly cheap to use and does return a heap of framebuffer bandwidth thanks to the higher frequency memory. Also I can imagine a simpler design in the PCB such as using less wires and thus a cheaper design. On the flip side, gDDR5 does have somewhat slower memory latency timings. But granted, this choice makes a lot of sense, as the benchmark results will show.

Now I've fired off some math at the most generic denominators and when we place things in a chart, you'll gain some perspective of product differences.

Geek facts: the RV740 houses 640 stream processors, 32 texture memory units (TMUs) and 16 render output units (abbreviated as ROPs). As stated, It features a 128-bit wide bus using GDDR5 memory, bumping up bandwidth that rivals equally clocked GDDR3 with double the bus width producing 51.2 GB/s of memory bandwidth, and for a product like shown today... bandwidth is everything.