Earlier Apple CPUs do not support SVE. Recent Apple CPUs support a certain variant of the so-called "streaming" SVE (which is included in the SME specification), which is implemented in a way that has poor performance, so it probably exists only for software compatibility, but its use is not recommended.
On Apple CPUs, the original 64-bit FP instructions must be used when low latency is important and SME must be used when high throughput is important.
Most Android smartphones that were launched on the market since around the beginning of 2022 support SVE, so by the end of this year there will be 5 years of availability.
Of course there are people who have not updated their smartphones. I still use an ASUS Zenfone from 2019, which precedes SVE (though I think that this year I might finally buy a new smartphone among those that use Mediatek 9500 or Exynos 2600, because I am curious to experiment with the new Arm SME2 instruction set). Among the cheapest smartphones, there are still sold some with old Cortex-A78 cores (launched in 2020), which do not support SVE.
NEON is an obsolete and inappropriate name, but I think that what you mean is that among the 64-bit Arm CPUs, all those that support SVE (which includes the CPUs of all recent so-called "gaming smartphones") also support the original Aarch64 floating-point instruction set, which is available in all 64-bit Arm CPUs that have been used in mobile phones, tablets or laptops.
The "and not Neon" was a bit of an unnecessary pre-condition I shouldn't have added. However, given the OP discusses "there were a surprising number of users without AVX2 capable CPUs", I think there would be an un-surprising number of users (for this type of library) without SVE. SVE feels analogous to some of AVX-512 at present -- maybe not that bad.
Do the Apple CPUs support SVE? If not then it's not worth the hassle tbh (and support on Android devices doesn't seem to be great either).
Earlier Apple CPUs do not support SVE. Recent Apple CPUs support a certain variant of the so-called "streaming" SVE (which is included in the SME specification), which is implemented in a way that has poor performance, so it probably exists only for software compatibility, but its use is not recommended.
On Apple CPUs, the original 64-bit FP instructions must be used when low latency is important and SME must be used when high throughput is important.
Most Android smartphones that were launched on the market since around the beginning of 2022 support SVE, so by the end of this year there will be 5 years of availability.
Of course there are people who have not updated their smartphones. I still use an ASUS Zenfone from 2019, which precedes SVE (though I think that this year I might finally buy a new smartphone among those that use Mediatek 9500 or Exynos 2600, because I am curious to experiment with the new Arm SME2 instruction set). Among the cheapest smartphones, there are still sold some with old Cortex-A78 cores (launched in 2020), which do not support SVE.
Name a few big products with SVE and not NEON, within the gaming market
NEON is an obsolete and inappropriate name, but I think that what you mean is that among the 64-bit Arm CPUs, all those that support SVE (which includes the CPUs of all recent so-called "gaming smartphones") also support the original Aarch64 floating-point instruction set, which is available in all 64-bit Arm CPUs that have been used in mobile phones, tablets or laptops.
The "and not Neon" was a bit of an unnecessary pre-condition I shouldn't have added. However, given the OP discusses "there were a surprising number of users without AVX2 capable CPUs", I think there would be an un-surprising number of users (for this type of library) without SVE. SVE feels analogous to some of AVX-512 at present -- maybe not that bad.
2 replies →