Version and / or Patch Used: 3.05
ATTO is a timeless benchmark used to provide manufacturers with data used for marketing storage products. When evaluating ATTO performance, we focus on the drive's performance curve.
As demonstrated by these benchmarks, the XG5 when running an OS, is bypassing the drive's SLC cache when writing sequential data. Keep in mind that this is by design as we will demonstrate when we get to our SYSmark testing.
Graphing the performance curve shows that without an OS on the disk, the XG5 sets a new lab record for sequential write performance. With an OS on the disk, data has been pinned to the drives SLC cache causing the drive to write directly to TLC.
We would like to see sequential read performance ramp up a bit quicker, but with or without an OS on the disk, the XG5 is able to meet or exceed its factory sequential read specification. At 32KB transfers or larger, the XG5 surpasses its predecessors; the XG3 and RD400. At 64KB transfers, the XG5 is able to surpass the PM961.
Anvil Storage Utilities
Version and / or Patch Used: 1.1.0
Anvil's Storage Utilities is a storage benchmark designed to measure the storage performance of SSDs. The Standard Storage Benchmark performs a series of tests; you can run a full test or just the read or write test, or you can run a single test, i.e. 4k QD16. When evaluating performance with Anvils, we focus on the total score. When evaluating NVMe SSDs, we are typically looking for a minimum total score of over 10K.
With or without an OS on the disk, the XG5 gives us our 10K minimum and then some. In either state, the XG5 is outperforming its predecessors. We are particularly pleased with the read performance of the XG5 when running as a secondary device where it once again shows better performance than its primary competitor the Samsung PM961. Again, we will reiterate that we believe the empty results of the XG5 will give us a reasonably accurate representation of what we can expect from OCZ's next generation NVMe SSD even with an OS on it and filled to 75% of its capacity.
(Anvil) Read IOPS through Queue Depth Scale
The way Anvil's, as well as most synthetic benchmarks work, is they write a test file then read it back. With an OS on the drive, the XG5 is unable to read cached data from its SLC cache, resulting significantly lower random read performance at QD32.
Because of the way the XG5 is programmed to pin data to its SLC cache when an OS is in place, the XG5 doesn't chart well with an OS on it. However, when running with an available SLC cache to read from, the XG5 turns into a beast that is able to easily outperform the PM961 and 960 EVO at queue-depths of up to 32.
(Anvil) Write IOPS through Queue Scale
Sequential write performance takes a big hit when an OS resides on the XG5, but random write performance is hardly affected when data is pinned to the drives SLC cache. This is due to Windows write caching boosting random write performance.
As mentioned, random write performance remains relatively unscathed when an OS is on the XG5. The Samsung contenders are able to generate incredible random write performance at high queue depths which is the primary reason they score higher. The RD400 outperforms the XG5 at queue depths of up to four. The XG5 and XG3 perform similarly at QD1-2. At QD8, the TLC powered XG5 is able to out-muscle its MLC powered predecessors.
PRICING: You can find the product discussed for sale below. The prices listed are valid at the time of writing, but can change at any time. Click the link below to see real-time pricing for the best deal:
United States: Find other tech and computer products like this over at the Amazon website.
United Kingdom: Find other tech and computer products like this over at the Amazon UK website.
Canada: Find other tech and computer products like this over at the Amazon Canada website.
- Page 1 [Introduction, Drive Specifications, Pricing & Availability]
- Page 2 [Drive Details]
- Page 3 [Test System Setup & Drive Properties]
- Page 4 [Synthetic Benchmarks – ATTO & Anvil Storage Utilities]
- Page 5 [Synthetic Benchmarks - CrystalDiskMark & AS SSD]
- Page 6 [Benches (OS) - Vantage, PCMark 7, PCMark 8 & SYSmark 2014 SE]
- Page 7 [Benchmarks (Secondary) - IOPS, Response & Transfer Rate]
- Page 8 [Benchmarks – 70/30 Mixed Workload & Sustained Sequential Write]
- Page 9 [Maxed-Out Performance (MOP)]
- Page 10 [Final Thoughts]