Stream: git-wasmtime

Topic: wasmtime / PR #2355 CL/aarch64: implement the wasm SIMD `...

Wasmtime GitHub notifications bot (Nov 03 2020 at 16:35):

julian-seward1 opened PR #2355 from arm64-simd-loadzero to main:

…ons.

This patch implements, for aarch64, the following wasm SIMD extensions.

v128.load32_zero and v128.load64_zero instructions
https://github.com/WebAssembly/simd/pull/237

The changes are straightforward:

• no new CLIF instructions. They are translated into an existing CLIF scalar
  load followed by a CLIF scalar_to_vector.

• the comment/specification for CLIF scalar_to_vector has been changed to
  match the actual intended semantics, per consulation with Andrew Brown.

• translation from scalar_to_vector to the obvious aarch64 insns.

• special-case zero in lower_constant_f128 in order to avoid a
  potentially slow call to Inst::load_fp_constant128.

• Once "Allow loads to merge into other operations during instruction
  selection in MachInst backends"
  (https://github.com/bytecodealliance/wasmtime/issues/2340) lands,
  we can use that functionality to pattern match the two-CLIF pair and
  emit a single AArch64 instruction.

There is no testcase in this commit, because that is a separate repo. The
implementation has been tested, nevertheless.

<!--

Please ensure that the following steps are all taken care of before submitting
the PR.

• [ ] This has been discussed in issue #..., or if not, please tell us why
  here.

• [ ] A short description of what this does, why it is needed; if the
  description becomes long, the matter should probably be discussed in an issue
  first.

• [ ] This PR contains test cases, if meaningful.

• [ ] A reviewer from the core maintainer team has been assigned for this PR.
  If you don't know who could review this, please indicate so. The list of
  suggested reviewers on the right can help you.

Please ensure all communication adheres to the code of conduct.
-->

Wasmtime GitHub notifications bot (Nov 03 2020 at 16:40):

julian-seward1 updated PR #2355 from arm64-simd-loadzero to main:

…ons.

This patch implements, for aarch64, the following wasm SIMD extensions.

v128.load32_zero and v128.load64_zero instructions
https://github.com/WebAssembly/simd/pull/237

The changes are straightforward:

• no new CLIF instructions. They are translated into an existing CLIF scalar
  load followed by a CLIF scalar_to_vector.

• the comment/specification for CLIF scalar_to_vector has been changed to
  match the actual intended semantics, per consulation with Andrew Brown.

• translation from scalar_to_vector to the obvious aarch64 insns.

• special-case zero in lower_constant_f128 in order to avoid a
  potentially slow call to Inst::load_fp_constant128.

• Once "Allow loads to merge into other operations during instruction
  selection in MachInst backends"
  (https://github.com/bytecodealliance/wasmtime/issues/2340) lands,
  we can use that functionality to pattern match the two-CLIF pair and
  emit a single AArch64 instruction.

There is no testcase in this commit, because that is a separate repo. The
implementation has been tested, nevertheless.

<!--

Please ensure that the following steps are all taken care of before submitting
the PR.

• [ ] This has been discussed in issue #..., or if not, please tell us why
  here.

• [ ] A short description of what this does, why it is needed; if the
  description becomes long, the matter should probably be discussed in an issue
  first.

• [ ] This PR contains test cases, if meaningful.

• [ ] A reviewer from the core maintainer team has been assigned for this PR.
  If you don't know who could review this, please indicate so. The list of
  suggested reviewers on the right can help you.

Please ensure all communication adheres to the code of conduct.
-->

Wasmtime GitHub notifications bot (Nov 03 2020 at 17:06):

abrown submitted PR Review.

Wasmtime GitHub notifications bot (Nov 03 2020 at 17:13):

julian-seward1 requested yurydelendik for a review on PR #2355.

Wasmtime GitHub notifications bot (Nov 03 2020 at 17:18):

cfallin submitted PR Review.

Wasmtime GitHub notifications bot (Nov 03 2020 at 18:52):

akirilov-arm submitted PR Review.

Wasmtime GitHub notifications bot (Nov 03 2020 at 18:52):

akirilov-arm submitted PR Review.

Wasmtime GitHub notifications bot (Nov 03 2020 at 18:52):

akirilov-arm created PR Review Comment:

This should simply be Inst::MovToFpu, and then there is no need for lower_constant_f128().

BTW if the original load is a FP load, then this could be a move.

Wasmtime GitHub notifications bot (Nov 04 2020 at 10:31):

julian-seward1 submitted PR Review.

Wasmtime GitHub notifications bot (Nov 04 2020 at 10:31):

julian-seward1 created PR Review Comment:

From reading of FMOV (general), I don't see anything that implies that lanes 1 and above of the destination register are zeroed. I may well have missed it though; can you clarify?

Wasmtime GitHub notifications bot (Nov 04 2020 at 13:00):

akirilov-arm submitted PR Review.

Wasmtime GitHub notifications bot (Nov 04 2020 at 13:00):

akirilov-arm created PR Review Comment:

The pseudocode for FMOV (general) uses the assignment form of Vpart[], which zero-extends the written value if part is 0, as the comments in the pseudocode state.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:16):

julian-seward1 updated PR #2355 from arm64-simd-loadzero to main:

…ons.

This patch implements, for aarch64, the following wasm SIMD extensions.

v128.load32_zero and v128.load64_zero instructions
https://github.com/WebAssembly/simd/pull/237

The changes are straightforward:

• no new CLIF instructions. They are translated into an existing CLIF scalar
  load followed by a CLIF scalar_to_vector.

• the comment/specification for CLIF scalar_to_vector has been changed to
  match the actual intended semantics, per consulation with Andrew Brown.

• translation from scalar_to_vector to the obvious aarch64 insns.

• special-case zero in lower_constant_f128 in order to avoid a
  potentially slow call to Inst::load_fp_constant128.

• Once "Allow loads to merge into other operations during instruction
  selection in MachInst backends"
  (https://github.com/bytecodealliance/wasmtime/issues/2340) lands,
  we can use that functionality to pattern match the two-CLIF pair and
  emit a single AArch64 instruction.

There is no testcase in this commit, because that is a separate repo. The
implementation has been tested, nevertheless.

<!--

Please ensure that the following steps are all taken care of before submitting
the PR.

• [ ] This has been discussed in issue #..., or if not, please tell us why
  here.

• [ ] A short description of what this does, why it is needed; if the
  description becomes long, the matter should probably be discussed in an issue
  first.

• [ ] This PR contains test cases, if meaningful.

• [ ] A reviewer from the core maintainer team has been assigned for this PR.
  If you don't know who could review this, please indicate so. The list of
  suggested reviewers on the right can help you.

Please ensure all communication adheres to the code of conduct.
-->

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:18):

julian-seward1 submitted PR Review.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:18):

julian-seward1 created PR Review Comment:

I rewrote it to generate FMOV only.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:39):

akirilov-arm submitted PR Review.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:47):

akirilov-arm submitted PR Review.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:47):

akirilov-arm created PR Review Comment:

BTW I don't mind the comment at al, but this operation is not special - virtually any instruction that operates on S or D registers (e.g. Inst::FpuRR) has exactly the same behaviour.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:50):

julian-seward1 requested cfallin and yurydelendik for a review on PR #2355.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:53):

cfallin submitted PR Review.

Wasmtime GitHub notifications bot (Nov 04 2020 at 18:54):

akirilov-arm edited PR Review Comment.

Wasmtime GitHub notifications bot (Nov 04 2020 at 19:00):

julian-seward1 merged PR #2355.

Last updated: Oct 23 2024 at 20:03 UTC