The BG4 is Toshiba's fourth-generation ball grid array SSD, combining NAND and controller in a single package. The new BG4 is a big step forward from the previous BG3 using Toshiba's latest NAND technology and a new controller. The BG4 uses Toshiba's latest 96-layer BiCS4 3D TLC NAND and comes in four capacities; 128GB, 256GB, 512GB and the flagship 1TB drive. There are two formats; M.2 surface-mount 1620 single package (coded KBG40ZPZ) and removable M.2 2230 module (coded KBG40ZNS). It's the latter we are looking at here, with the 1TB KBG40ZNS1T02 flagship drive. The previous generation drive, the BG3, used a controller with a PCIe 3 x2 interface, which has been replaced in the BG4 with one that supports PCIe 3 x4. Instead of a DRAM cache it uses NVMe Host Memory Buffer (HMB) technology, which uses a portion of host memory (less than 100MB) to support caching demands. Official performance figures for the 1TB drive are up to 2,300MB/s and up to 1,800MB/s for Sequential read/writes respectively with 4K random performance rated as up to 390,000 IOPS for reads and up to 200,000 IOPS for random writes. Physical Specifications: Usable Capacities: 1TB. NAND Components: Toshiba 96-layer BiCS4 3D TLC. NAND Controller: Toshiba. Interface: PCIe Gen3 x4 NVMe 1.3. Form Factor: M.2 2230-S3. Dimensions: 2.38 x 22 x 30mm. Firmware Version: AEJA0102. The 1TB module version of the BG4, coded KBG40ZNS, is built on a M.2 2230 format measuring just 2.38 x 22 x 30mm. A DRAM-less design, the drive has the controller and NAND combined into a single package. To give an idea of just how small the BG4 is, here it is next to a standard SD card. For testing, the drives are all wiped and reset to factory settings by HDDerase V4. We try to use free or easily available programs and some real world testing so you can compare our findings against your own system. This is a good way to measure potential upgrade benefits. Main system: Intel Core i7-7700K with 16GB of DDR4-3200 RAM, Sapphire R9 390 Nitro and an Asus Prime Z270-A motherboard. Other drives: Corsair Force MP500 480GB Corsair Force MP510 960GB Crucial P1 1TB Gigabyte Aorus RGB 512GB Intel Optane SSD900P 480GB Intel Optane SSD905P 480GB Intel SSD760p 512GB Kingston A1000 480GB Lexar NM600 480GB Plextor M9Pe(Y) 512GB Plextor M8PeG 512GB Patriot Viper VPN100 1TB PNY CS3030 1TB PNY CS2030 240GB Seagate FireCuda 510 1TB Samsung SSD970 EVO 2TB Samsung SSD970 PRO 1TB Samsung SSD960 PRO 2TB Samsung SSD960 EVO 1TB Samsung SSD960 EVO Plus 1TB Toshiba XG6 1TB Toshiba OCZ RD400 512GB Western Digital Black SN750 1TB Western Digital Black SN750 1TB with Heatsink Western Digital Black NVMe 1TB Western Digital Black PCIe 512GB Software: Atto Disk Benchmark 3.05. CrystalMark 6.0.0. AS SSD 2.0. IOMeter. Futuremark PC Mark 8 All our results were achieved by running each test five times with every configuration this ensures that any glitches are removed from the results. Trim is confirmed as running by typing fsutil behavior query disabledeletenotify into the command line. A response of disabledeletenotify =0 confirms TRIM is active. CrystalDiskMark is a useful benchmark to measure theoretical performance levels of hard drives and SSDs. We are using v6.0. The 1TB BG4 is faster than the previous Toshiba OEM drive we reviewed, the 1TB XG6, in the CrystalDiskMark benchmark at a QD of 32. The BG4 produced read/write figures of 494MB/s and 369.8MB/s respectively compared to the 406.6MB/s read and 324MB/s write results of the XG6. At a QD of 1, once again the BG4 is faster than the XG6, but this time the gap is a lot narrower for both reads and writes. Looking at both benchmark result screens, the Toshiba controller in the BG4 doesn't seem to have a preference for which type of data it's being asked to handle. The ATTO Disk Benchmark performance measurement tool is compatible with Microsoft Windows. Measure your storage systems performance with various transfer sizes and test lengths for reads and writes. Several options are available to customise your performance measurement including queue depth, overlapped I/O and even a comparison mode with the option to run continuously. Use ATTO Disk Benchmark to test any manufacturers RAID controllers, storage controllers, host adapters, hard drives and SSD drives and notice that ATTO products will consistently provide the highest level of performance to your storage. We are using version 3.5 for our NVMe disk tests. The official Sequential performance figures for the 1TB BG4 is up to 2,300MB/s for reads and up to 1,800MB/s for writes, figures we could confirm with the ATTO benchmark - with the review drive producing reads of 2,422MB/s and writes of 1,879MB/s. AS SSD is a great free tool designed just for benching Solid State Drives. It performs an array of sequential read and write tests, as well as random read and write tests with sequential access times over a portion of the drive. AS SSD includes a sub suite of benchmarks with various file pattern algorithms but this is difficult in trying to judge accurate performance figures. The BG4 produces a faster read score of 1920 in the AS SSD benchmark than the other Toshiba OEM drive in the chart, the XG6 (1774), however when it comes to write performance the XG6 is a lot faster with a write score of 1935 compared to the 1159 of the BG4. IOMeter is another open source synthetic benchmarking tool which is able to simulate the various loads placed on hard drive and solid state drive technology. There are many ways to measure the IOPS performance of a Solid State Drive, so our results will sometimes differ from manufacturer’s quoted ratings. We do test all drives in exactly the same way, so the results are directly comparable. We test 128KB Sequential read and write and random read and write 4k tests. The test setup’s for the tests are listed below. Each is run five times. 128KB Sequential Read / Write. Transfer Request Size: 128KB Span: 8GB Thread(s): 1, Outstanding I/O: 1-32 Test Run: 20 minutes per test. 4K Sustained Random Read / Write. Transfer Request Size: 4KB Span: 80GB Thread(s): 4, Outstanding I/O: 1-32 Test Run: 20 minutes per test. 4K Random 70/30 mix Read/Write. Transfer Request Size: 4KB Span: 80GB Reads: 70% Writes: 30% Thread(s): 4 Outstanding I/O: 2 – 32 Test Run: 20 minutes. With our own Sequential testing we could also confirm the official 'up to 2,300MB/s' read and 'up to 1,800MB/s' for write figures, the review BG4 producing a read figure of 2,418.75MB/s with writes at 1,861.66MB/s. 128KB Sequential Read Performance v QD The best performance from the BG4 in relation to the other drives around it in comes at QD4 where the drive sits mid table, before dropping back down as the QD increases. 128KB Sequential Write Performance v QD After an initial surge from QD1 to QD2, the write performance of the drive settles to a much consistent level through the rest of the test. The 1TB BG4 is rated at up to 390,000 IOPS for 4K random reads. Unfortunately with our 4 threaded tests we couldn't get close to this maximum figure, the best we got from the review drive was 247,013 IOPS. 4K Random Read v QD Performance At shallow queue depths the BG4 languishes at the bottom of our results charts, but the performance improves noticeably at a QD of 32 and it moves up the chart. When tested with our 4K random write tests using 4 threads, the results we got from the drive were disappointing to say the least. The best figure we got was 77,132 IOPS, nowhere close to the official maximum figure of 200,000 IOPS. 4K Random Write v QD Performance The tested 4K performance of the drive might be disappointing but apart from the QD1 result, the drive is very consistent. The drive's performance in our mixed read/write test was very erratic. Peak read throughput came at the 8MB block mark at 2,050.14MB/s, before falling back to finish the test run at 2,016.08MB/s. The BG4 read figure of 2,050.14MB/s is a fair bit off the pace compared to the 2,599MB/s of the previous Toshiba OEM drive we looked at, the XG6. . Peak writes came at the end of the test, at 1,306.51MB/s. When it comes to write throughput, the BG4 is light years behind Toshiba's XG6. Futuremark’s PCMark 8 is a very good all round system benchmark but it’s Storage Consistency Test takes it to whole new level when testing SSD drives. It runs through four phases; Preconditioning, Degradation, Steady State, Recovery and finally Clean Up. During the Degradation, Steady State and Recovery phases it runs performance tests using the 10 software programs that form the backbone of PCMark 8; Adobe After Effects, Illustrator, InDesign, Photoshop Heavy and Photoshop Light, Microsoft Excel, PowerPoint, Word, Battlefield 3 and World of Warcraft. With some 18 phases of testing, this test can take many hours to run. Preconditioning The drive is written sequentially through up to the reported capacity with random data, write size of 256 × 512 = 131,072 bytes. This is done twice. Degradation Run writes of random size between 8 × 512 and 2048 × 512 bytes on random offsets for 10 minutes. It then runs a performance test. These two actions are then repeated 8 times and on each pass the duration of random writes is increased by 5 minutes. Steady State Run writes of random size between 8 × 512 and 2048 × 512 bytes on random offsets for final duration achieved in degradation phase. A performance test is then run. These actions are then re-run five times. Recovery The drive is idled for 5 minutes. Then a performance test is run. These actions are then repeated five times. Clean Up The drive is written through sequentially up to the reported capacity with zero data, write size of 256 × 512 = 131,072 bytes. Overall the 1TB BG4 handles the PCM8 Consistency Test reasonably well. It gets hit hard during the latter stages of the Degradation phases but it does pull back the performance during the Steady State test runs and the recovery is good but erratic. PCMark 8’s Consistency test provides a huge amount of performance data, so here we’ve looked a little closer at how the BG4 performs in each of the benchmarks test suites. Adobe Creative Cloud The drive doesn't handle the Adobe CC test to well at all, with the Adobe Photoshop Heavy, Photoshop Light and Indesign tests all struggling for bandwidth throughout the Degradation and Steady State phases. There is a huge performance spike in the first recovery run of the Indesign test trace, but it very rapidly drops back down. Microsoft Office The drive also struggles with the MS Office part of the test. It’s usually the MS Office trace that causes most problems but with the BG4, all three test traces causes it problems during the latter stages of the Degradation phases. The drive does stage a remarkable recovery during the most of the Steady State runs but, very oddly the performance drops again during the early Recovery phases. Casual Gaming The performance of the drive during the Casual Gaming tests is erratic to say the least. The drive makes a decent start to the Recovery phase for both game tests but unfortunately, the performance tails off during the last Recovery run. Just like the Consistency test, PCMark 8’s Standard Storage test also saves a large amount of performance data. The default test runs through the test suite of 10 applications three times. Here we show the total bandwidth performance for each of the individual test suites for the third and final benchmark run. The BG4 shows strong performance for all of the applications in PCMark 8's Standard Storage test, but the two Adobe Photoshop traces do particularly well. The total test bandwidth figure for the drive of 713.72MB/s is very good. If you take the two Intel Optane drives out of the picture, the BG4 sits in second place behind Samsung's mighty SSD970 PRO. For the long term performance stability test, we set the drive up to run a 20-minute 4K random test with a 30% write, 70% read split, at a Queue Depth of 256 over the entire disk. The 1TB Toshiba BG4 averaged 23,935 IOPS for the test with a performance stability of 70%. To test real life performance of a drive we use a mix of folder/file types and by using the FastCopy utility (which gives a time as well as MB/s result) we record the performance of drive reading from & writing to a 256GB Samsung SSD850 PRO. We use the following folder/file typesL 100GB data file. 60GB iso image. 60GB Steam folder – 29,521 files. 50GB File folder – 28,523 files. 21GB 8K Movie demos. 12GB Movie folder – 24 files (mix of Blu-ray and 4K files). 11GB 4K Raw Movie Clips (8 MP4V files). 10GB Photo folder – 621 files (mix of png, raw and jpeg images). 10GB Audio folder – 1,483 files (mix of mp3 and .flac files). 5GB (1.5bn pixel) photo. Blu-ray movie. The 1TB Toshiba BG4 handled our real life file transfer tests without missing a beat. It's much more efficient at dealing with larger file sizes than small bity ones as can be seen by the results for the 60GB Steam, 50GB file and 10GB audio tests. To get a measure of how much faster PCIe NVMe drives are than standard SATA SSDs, we use the same files but transfer to and from a 512GB Toshiba OCZ RD400: Transferring the files to and from another NVMe drive shows just how quick the BG4 is at handling file transfers especially when it comes to reading the data. The BG4, Toshiba's fourth generation ball grid array (BGA) drive, is a tiny SSD - basically not that much bigger than a NAND package, or just a bit smaller than a standard SD flash card. It's possible for the drive to be made this small because the controller and flash are combined in a single package. An OEM part at present, Toshiba are aiming the BG4 at ultra-mobile and 2-in-1 notebook PCs, IoT/embedded devices and as boot drives for server and storage arrays. The drive uses Toshiba's latest 96-layer BiCS4 3D TLC NAND and a new PCIe 3 x4 controller. This is a large leap forward from the previous BG2 and BG3 models which used 64-layer NAND and a PCIe 3 x2 controller. Despite its small size the BG4 comes in four capacities; 128GB, 256GB, 512GB and 1TB and in two formats - surface mounted M.2 1620 or module mounted M.2 2230. When it comes to Sequential performance, the official figures for the 1TB drive are rated at up to 2,300MB/s for reads and up to 1,800MB/s for writes. Both of those figures we were able to confirm using the ATTO benchmark, with the review drive producing read figures of 2,422MB/s and writes of 1,879MB/s. The 4K random performance, on the other hand, was disappointing. The official maximum 4K random read figure is rated at up to 390,000 IOPS, but the best we could get out of the drive was 247,013 IOPS. Write performance was even worse, the best figure we got from our 4-threaded test was 77,132 IOPS - nowhere close to the official rating of up to 200,000 IOPS. That aside, we think it is still amazing that a drive this small can not only have up to 1TB in capacity but also have Sequential read/write speeds of 2,300MB/s and 1,800MB/s respectively. 4K random performance isn't great, but the BG4 provides the opportunity for manufacturers of ultra-portables and other very small format systems to install some fast storage. Pros Compact size. Sequential performance. Cons OEM part only at present. Tested 4K performance was disappointing. KitGuru says: Although an OEM part, the BG4 may well find its way to the consumer space in the not too distant future.
KitGuru KitGuru.net – Tech News | Hardware News | Hardware Reviews | IOS | Mobile | Gaming | Graphics Cards
