diff options
| author | Dan Gohman <sunfish@mozilla.com> | 2015-05-12 15:41:58 -0700 |
|---|---|---|
| committer | Dan Gohman <sunfish@mozilla.com> | 2015-05-14 08:26:07 -0700 |
| commit | c3e8d2cc7370cab786a4ce6ed48ef15ec51019bf (patch) | |
| tree | 96f7371159be390ffddc4ac5909bb407f3cc0fac | |
| parent | fac3a4ca2be9104a4b3780f032dcd2341ae738c7 (diff) | |
| download | nanowasm-design-c3e8d2cc7370cab786a4ce6ed48ef15ec51019bf.tar.gz | |
Materialize the section on "Long SIMD".
This is meant to address the original concern in
https://github.com/WebAssembly/spec/issues/41
| -rw-r--r-- | FutureFeatures.md | 24 |
1 files changed, 22 insertions, 2 deletions
diff --git a/FutureFeatures.md b/FutureFeatures.md index 0ec2d13..47836fa 100644 --- a/FutureFeatures.md +++ b/FutureFeatures.md @@ -93,8 +93,28 @@ This is covered in the [tooling](Tooling.md) section. ## Asynchronous Signals * TODO -## Non-fixed-width SIMD - * TODO +## "Long SIMD" +* The initial SIMD API will be a "short SIMD" API, centered around fixed-width + 128-bit types and explicit SIMD operations. This is quite portable and useful, + but it won't be able to deliver the full performance capabilities of some of + today's popular hardware. There is an opportunity for someone to propose a + "long SIMD" model which will generalize to wider hardware vector lengths make + more natural use of advanced features like vector lane predication, + gather/scatter, and so on. Interesting questions to ask of such an model will + include: + * How will this model map onto popular modern SIMD hardware architectures? + * What is this model's relationship to other hardware parallelism features, + such as GPUs and threads with shared memory? + * How will this model be used from higher-level programming languages? + For example, the C++ committee is considering a wide variety of possible + approaches; which of them might be supported by the model? + * What is the relationship to the "short SIMD" API? "None" may be an + acceptable answer, but it's something to think about. + * What non-determinism does this model introduce into the overall platform? + * What happens when code uses long SIMD on a hardware platform which doesn't + support it? Reasonable options may include emulating it without the + benefit of hardware acceleration, or indicating a lack of support through + feature tests. ## Operations which may not be available or may not perform well on all platforms * Fused multiply-add. |