1 00:00:00,080 --> 00:00:07,680 Now, as most of you probably know, NVIDIA acquired our company back in 2 00:00:04,319 --> 00:00:10,000 early Q2 of 2016. So, you can imagine 3 00:00:07,680 --> 00:00:16,240 how upset our Emerald overlords were when we decided to test 10 years worth 4 00:00:13,040 --> 00:00:19,920 of AMD video cards before giving the 5 00:00:16,240 --> 00:00:22,480 green team the same treatment. Well, we 6 00:00:19,920 --> 00:00:28,560 finally put out the fire in our server room and just in time to bring you the 7 00:00:25,439 --> 00:00:32,079 other side of the GPU performance coin. 8 00:00:28,560 --> 00:00:34,100 Welcome to NVIDIA video cards through 9 00:00:32,079 --> 00:00:39,069 the 10 00:00:42,120 --> 00:00:50,239 ages. Rockat's Plus Force FX features 11 00:00:46,239 --> 00:00:52,320 pressure sensitive QWES as keys which 12 00:00:50,239 --> 00:00:57,360 can be configured in three different modes for multiple functions. Check it 13 00:00:54,640 --> 00:01:02,559 out now at the link below. This is going to be a long video, so let's get right 14 00:00:59,520 --> 00:01:05,600 into it. We used a 5960X test bench with 15 00:01:02,559 --> 00:01:08,479 64 gigs of DDR4 RAM to isolate the 16 00:01:05,600 --> 00:01:14,880 performance of the graphics cards. And we used the same benchmarks as AMD GPUs 17 00:01:11,920 --> 00:01:21,840 through the ages for consistency. First up is NVIDIA's ancient flagship, the 18 00:01:18,080 --> 00:01:24,560 8800 GTX. This card was freaking 19 00:01:21,840 --> 00:01:32,280 revolutionary. It brought us an all new architecture called Tesla in the biggest 20 00:01:27,759 --> 00:01:35,920 chip we had ever seen in a GPU code name 21 00:01:32,280 --> 00:01:39,759 G80. It was built on the same 90mm 22 00:01:35,920 --> 00:01:44,000 process node as its predecessor G71, but 23 00:01:39,759 --> 00:01:47,200 was over twice as big with almost 2 and 24 00:01:44,000 --> 00:01:50,240 1/2 times as many transistors devoted to 25 00:01:47,200 --> 00:01:52,560 gaming performance, enabling new DirectX 26 00:01:50,240 --> 00:01:57,520 10 features like SM 4.0 0 and a reduction in API overhead. CUDA, which 27 00:01:55,680 --> 00:02:02,719 is still very much in use today and enabled developers to run generalpurpose 28 00:01:59,840 --> 00:02:08,479 code on the graphics chip and the ability to run three cards at once in 29 00:02:05,960 --> 00:02:14,560 SLI, which isn't to say that its standalone performance wasn't impressive 30 00:02:10,640 --> 00:02:19,120 in its own right. G80 with its 768 megs 31 00:02:14,560 --> 00:02:22,319 of GDDR3 RAM on a wide 384-bit bus 32 00:02:19,120 --> 00:02:25,360 smacked around even two of NVIDIA's 33 00:02:22,319 --> 00:02:28,080 previous flagships in SLI. And all of 34 00:02:25,360 --> 00:02:32,560 that for a measly $100 more, which almost makes me feel better about the 35 00:02:29,840 --> 00:02:37,760 cash grab 8800 Ultra that they released 6 months later for $230 more that was 36 00:02:35,519 --> 00:02:45,360 basically the same thing with a fancy plastic shroud on it. The GeForce 8800 37 00:02:41,800 --> 00:02:48,560 GT wasn't strictly speaking a new 38 00:02:45,360 --> 00:02:51,519 flagship, but rather a weird Tesla 39 00:02:48,560 --> 00:02:58,160 architecture refresh. It was the first built by NVIDIA on TSMC's shiny new 65 40 00:02:55,200 --> 00:03:04,640 nanometer process. This node shrink allowed NVIDIA to drop power consumption 41 00:03:00,480 --> 00:03:07,360 by 60 watts, reduce the die size, and 42 00:03:04,640 --> 00:03:12,640 actually bump up the transistor count at the same time. a modest increase that 43 00:03:10,720 --> 00:03:20,959 you guessed it. No, actually you probably didn't. The 8800 GT was on par 44 00:03:16,800 --> 00:03:23,440 or slower than its predecessor almost 45 00:03:20,959 --> 00:03:30,239 across the board due to its narrower memory bus and 16 fewer shader units. 46 00:03:27,040 --> 00:03:34,159 Where people got excited was the price. 47 00:03:30,239 --> 00:03:38,400 8800 GT was less than half the price of 48 00:03:34,159 --> 00:03:41,280 8800 GTX. It was single slot, enabling 49 00:03:38,400 --> 00:03:46,640 MATX users to run to an SLI with additional expansion cards, and it also 50 00:03:43,599 --> 00:03:49,440 featured an onchip display engine. 51 00:03:46,640 --> 00:03:55,760 Finally, it was the first consumer GPU with a PCI Express 2.0 interface, which 52 00:03:52,640 --> 00:03:58,319 still to this day is barely saturated by 53 00:03:55,760 --> 00:04:03,120 flagship graphics cards. The last flagship silicon before NVIDIA 54 00:04:00,480 --> 00:04:08,560 transitioned to the GTX insert three numbers and maybe a couple letters here 55 00:04:05,000 --> 00:04:12,159 nomenclature was G92, the beating heart 56 00:04:08,560 --> 00:04:15,040 of the 9800 GTX Plus, a skew that 57 00:04:12,159 --> 00:04:22,479 lowered NVIDIA's cost and bumped up performance over the architecturally 58 00:04:17,680 --> 00:04:25,919 identical 9800 GTX by shrinking from 65 59 00:04:22,479 --> 00:04:30,560 to 55 nm and boosting up the clock 60 00:04:25,919 --> 00:04:32,800 speed. Now we get to the GTX 280. Yes, 61 00:04:30,560 --> 00:04:36,639 we know it actually came out before that last one I was talking about, but deal 62 00:04:34,880 --> 00:04:45,240 with it. So, forget everything we said earlier about 55 nanmter. The 280 built 63 00:04:40,160 --> 00:04:50,400 on the mature 65nm process had a massive 64 00:04:45,240 --> 00:04:53,680 576 mm die with 1.4 billion transistors. 65 00:04:50,400 --> 00:04:57,120 And to put that insanity in context, 66 00:04:53,680 --> 00:04:58,360 AMD's closest competitor, the 4870 had a 67 00:04:57,120 --> 00:05:04,240 measly 959 million. And further driving up 68 00:05:01,520 --> 00:05:11,520 complexity, it shipped with a minimum of 1 Gigabyte of graphics memory on a huge 69 00:05:08,440 --> 00:05:15,280 512bit bus, something NVIDIA hasn't done 70 00:05:11,520 --> 00:05:17,919 before or since on a consumer card. The 71 00:05:15,280 --> 00:05:22,479 good news is that it absolutely crushed their previous generation efforts, even 72 00:05:20,400 --> 00:05:28,160 delivering ample performance for stereoscopic 3D gaming, a big push for 73 00:05:25,360 --> 00:05:32,479 NVIDIA at that time. We'll skip over the 300 series because all of these were 74 00:05:30,240 --> 00:05:39,440 just crappy rebrands for notebooks and Best Buy PCs, meaning that the next real 75 00:05:35,199 --> 00:05:42,880 GPU in line is the GTX 480 based on the 76 00:05:39,440 --> 00:05:46,000 then all-new and now infamous Fermy 77 00:05:42,880 --> 00:05:48,720 architecture. This was NVIDIA's first 78 00:05:46,000 --> 00:05:53,440 swing at DirectX11 support, which is still widely used today. And this is 79 00:05:51,680 --> 00:05:59,440 becoming a bit of a common theme. But while the new 40nm process allowed it to 80 00:05:56,479 --> 00:06:08,800 be smaller than the GTX 280, it was still huge with a 529 millimeter die, a 81 00:06:04,759 --> 00:06:12,560 wamping 3 billion transistors, and 82 00:06:08,800 --> 00:06:15,759 support for DDDR5 memory, which again is 83 00:06:12,560 --> 00:06:18,160 still widely used today. Interesting 84 00:06:15,759 --> 00:06:24,319 fact, NVIDIA apparently thought it performed so well not just in gaming but 85 00:06:21,600 --> 00:06:30,880 also in compute which was a big focus for Fermy that the largest configuration 86 00:06:27,440 --> 00:06:33,680 of GF100 silicon never actually made its 87 00:06:30,880 --> 00:06:39,840 way into a shipping product. Or maybe that was due to power constraints. Cuz 88 00:06:36,120 --> 00:06:42,000 uh yeah, even with the theoretical 89 00:06:39,840 --> 00:06:47,360 efficiency advantage of a smaller node, the 480 was such a barbecue that NVIDIA 90 00:06:45,120 --> 00:06:54,000 provided a convenient grill on the face of the card to cook your eggs. Our next 91 00:06:50,880 --> 00:06:56,960 contestant is the GTX 580, and it 92 00:06:54,000 --> 00:07:03,680 featured an optimized and fully enabled Fermy dubbed GF 110. We've got most of 93 00:07:00,960 --> 00:07:09,280 the usual improvements here. more VRAMm, higher clock speeds, and a slightly 94 00:07:06,319 --> 00:07:14,240 smaller die, but nothing as exciting as video card cooking, which we mean in a 95 00:07:11,599 --> 00:07:19,639 good way. 580 performed noticeably better than 480 while also managing 96 00:07:16,720 --> 00:07:25,599 lower temperatures, noise, and power consumption. It was kind of like the GTX 97 00:07:23,000 --> 00:07:29,919 480S, if that makes sense to the Apple fans out there. In the seventh corner of 98 00:07:28,319 --> 00:07:37,440 our showdown, this must be a weird looking ring. We have the GTX 680. Ah, 99 00:07:33,759 --> 00:07:40,800 yes. Goodbye Fermy. Hello Kepler. A lot 100 00:07:37,440 --> 00:07:45,039 of things changed here. 4K 60 Hz output 101 00:07:40,800 --> 00:07:47,759 was enabled via DisplayPort 1.2. PCI 102 00:07:45,039 --> 00:07:56,479 Express 3.0 burst onto the scene with double the bandwidth of version two. The 103 00:07:50,400 --> 00:08:00,479 die size shrunk way down to 294 mm. And 104 00:07:56,479 --> 00:08:02,879 the GDDR5 got kicked up a notch to 6 GHz 105 00:08:00,479 --> 00:08:10,120 thanks to a newly redesigned memory controller. Finally, we got it. Wait a 106 00:08:06,160 --> 00:08:13,400 minute. We dropped down to a 256 bit 107 00:08:10,120 --> 00:08:17,039 bus. Hold on a sec. Look at that code 108 00:08:13,400 --> 00:08:20,160 name. NVIDIA top tier chips usually end 109 00:08:17,039 --> 00:08:23,680 in a zero. Well, what they did was they 110 00:08:20,160 --> 00:08:26,400 used AMD's complacency and a new 28nmter 111 00:08:23,680 --> 00:08:33,279 process along with some dynamic power tricks called GPU Boost to crank up 112 00:08:29,759 --> 00:08:36,560 performance so much that they gave us a 113 00:08:33,279 --> 00:08:39,519 stepdown chip as a replacement for a top 114 00:08:36,560 --> 00:08:44,159 tier one to save a buck and still manage to make it look like an upgrade. Not 115 00:08:42,240 --> 00:08:50,000 that they passed any of those savings to the consumer. It was priced at $500, 116 00:08:47,279 --> 00:08:56,160 same as the GTX 580. Though, I guess at least we got hardware H.264 encoding for 117 00:08:53,360 --> 00:09:01,839 game stream and Shadow Play, G-Sync variable refresh rate technology, and 118 00:08:58,640 --> 00:09:04,000 support for the Vulcan API. Now, the 119 00:09:01,839 --> 00:09:11,839 next logical stop in our journey might seem like GTX 780, but in February 2013, 120 00:09:08,959 --> 00:09:20,240 NVIDIA kicked convention and logic in the head with a Titan card based on the 121 00:09:16,399 --> 00:09:22,959 chip that might have been GTX 680 in a 122 00:09:20,240 --> 00:09:30,800 parallel universe where AMD had been keeping up, but instead it turned into 123 00:09:26,560 --> 00:09:32,640 780 and then 780 Ti. So, we're going to 124 00:09:30,800 --> 00:09:40,800 go with that since it was kind of the final form of the GK 110. Now, not much 125 00:09:37,360 --> 00:09:44,320 changed product or feature-wise here. 126 00:09:40,800 --> 00:09:48,240 Big Kepler was a much bigger, much 127 00:09:44,320 --> 00:09:50,080 better 680 with a 90% bigger die, more 128 00:09:48,240 --> 00:09:57,279 than double the transistors at a whopping 7 billion, and a $699 price tag 129 00:09:53,920 --> 00:09:59,760 to go with it. Ouch. At least though, 130 00:09:57,279 --> 00:10:07,040 this amounted to a sizable bump in performance over last generation's 680 131 00:10:04,560 --> 00:10:12,399 in basically every application. In another unconventional move, NVIDIA 132 00:10:09,519 --> 00:10:18,480 completely skipped over 800 series and went straight to 900. So, even though 133 00:10:15,200 --> 00:10:20,079 the 980 and the 980 Ti were 9 months 134 00:10:18,480 --> 00:10:25,040 apart, we're going to bunch them together cuz apparently that's what 135 00:10:22,480 --> 00:10:31,440 everybody's doing. So, the 900 series was actually based on the same 28nm 136 00:10:27,839 --> 00:10:34,560 process as Kepler. Shrinking silicon got 137 00:10:31,440 --> 00:10:36,959 a lot harder in the early 2010s, but 2 138 00:10:34,560 --> 00:10:43,680 years later, we were due for some kind of performance improvement. So, NVIDIA's 139 00:10:39,680 --> 00:10:46,480 engineers brought us Maxwell. These GPUs 140 00:10:43,680 --> 00:10:50,480 feature an integrated ARM CPU, which according to NVIDIA provides more 141 00:10:48,480 --> 00:10:58,079 independence from a given systems primary CPU. The 980, again a step down 142 00:10:55,360 --> 00:11:04,000 chip in big kid clothes, performs a little better than the Kepler GTX 780 143 00:11:00,720 --> 00:11:08,320 Ti, which is an impressive feat. But the 144 00:11:04,000 --> 00:11:12,079 big story is efficiency. It boasts an 85 145 00:11:08,320 --> 00:11:14,320 watt lower TDP. The 980 Ti was a bit of 146 00:11:12,079 --> 00:11:19,839 a different story, though. It rocked 8 billion transistors, an unheard of 601 147 00:11:17,519 --> 00:11:26,640 square millimeter die, NVIDIA's biggest ever, 6 gigs of VRAM, and all the API 148 00:11:23,920 --> 00:11:32,240 support you could ever want, except maybe DirectX12, depending on who you 149 00:11:29,120 --> 00:11:34,480 ask. While Maxwell was marketed as fully 150 00:11:32,240 --> 00:11:39,279 DirectX12 capable, the developer of Ashes of the Singularity, Oxide Games, 151 00:11:37,120 --> 00:11:44,000 found that Maxwell cards performed very poorly with Async compute enabled, which 152 00:11:41,839 --> 00:11:49,040 is kind of a big deal. So, all of this amounted to an astonishing performance 153 00:11:46,079 --> 00:11:54,320 improvement considering the lack of process node change, and HDMI 2.0 154 00:11:51,760 --> 00:12:00,959 support was a nice touch. Finally, we arrive at the modern day. 155 00:11:57,040 --> 00:12:04,800 The GTX 1080 and 1080 Ti based on the 156 00:12:00,959 --> 00:12:06,800 Pascal architecture. 10 series GPUs have 157 00:12:04,800 --> 00:12:14,399 brought a lot to the table, including GDDR 5X at the top end, which increased 158 00:12:10,560 --> 00:12:18,480 memory speeds to up to 10 GHz. Multiple 159 00:12:14,399 --> 00:12:21,519 DisplayPort 1.4 four ports for 8K and 160 00:12:18,480 --> 00:12:24,399 high refresh 4K monitor support, high 161 00:12:21,519 --> 00:12:30,959 bandwidth SLI bridges, not to mention the elimination of 3-way and 4-way SLI 162 00:12:28,800 --> 00:12:38,800 for gaming, and the smallest manufacturing node yet, 16 nanmter. 1080 163 00:12:35,200 --> 00:12:40,959 launched in May of 2016 with 7.2 billion 164 00:12:38,800 --> 00:12:45,519 transistors. And this is becoming a pattern now, a small performance 165 00:12:42,480 --> 00:12:48,560 improvement over the 980 Ti. Then 1080 166 00:12:45,519 --> 00:12:50,959 Ti followed with a much more substantial 167 00:12:48,560 --> 00:12:57,279 bump. One of the biggest stories here though was really compute. Pascal was 168 00:12:54,079 --> 00:13:01,000 designed to be a compute powerhouse with 169 00:12:57,279 --> 00:13:05,839 the top tier GP100 chip going actually 170 00:13:01,000 --> 00:13:09,279 unused in gaming products. So 1080 Ti 171 00:13:05,839 --> 00:13:15,600 and its Titan analog were instead based 172 00:13:09,279 --> 00:13:15,600 on GP 102, a new in between tier. 173 00:13:16,880 --> 00:13:23,279 The ingenious EWS 360AP is an enterprise 174 00:13:20,720 --> 00:13:28,320 class dualband access point that's ideal for large offices, schools, and 175 00:13:25,680 --> 00:13:34,160 hospitality guest Wi-Fi access. It features AC speeds with business class 176 00:13:31,200 --> 00:13:39,440 features and operates in autonomous or managed modes. It's got a 3x3 antenna 177 00:13:37,120 --> 00:13:43,519 design and a high-owered radio and comes with a free management software called 178 00:13:41,519 --> 00:13:50,160 Easy Master. You can manage anywhere from one access point to thousands. And 179 00:13:46,560 --> 00:13:52,399 there are no per device license fees. So 180 00:13:50,160 --> 00:13:57,360 that means no annual subscription, which is great for keeping the total cost of 181 00:13:54,800 --> 00:14:02,680 ownership down. Check it and other ingenious products out over at their 182 00:13:59,120 --> 00:14:05,120 website through the link in the video 183 00:14:02,680 --> 00:14:08,880 description. Thanks for watching NVIDIA GPUs through the ages. If this video 184 00:14:07,279 --> 00:14:12,880 sucked, you know what to do. But if it was awesome, get subscribed, hit the like button, or check out the link to 185 00:14:11,199 --> 00:14:16,160 where to buy the stuff we featured in the video description. Also linked down 186 00:14:14,800 --> 00:14:23,399 there is our merch store, which has cool shirts like this one, and our community 187 00:14:18,399 --> 00:14:23,399 forum, which you should totally join.