Add Sk4h_load4 for loading F16.
authormtklein <mtklein@chromium.org>
Tue, 26 Jul 2016 15:01:19 +0000 (08:01 -0700)
committerCommit bot <commit-bot@chromium.org>
Tue, 26 Jul 2016 15:01:20 +0000 (08:01 -0700)
commitf660b7cfcfbf3062f88e61f8320ea7051da72213
treefca0db0effa07c70ea7f0b64f84b7f6e954c1944
parent8c523e0f3ffa66eefd70f893e9f863b7d9ea3dc9
Add Sk4h_load4 for loading F16.

Should feel very similar to Sk4h_store4:
NEON uses its native instruction, SSE unpacks manually.

Since we'll have our F16s in 4 Sk4h by the time we're done here,
this also extracts an Sk4h->Sk4f routine from the old uint64_t->Sk4f one.

BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2184753002
CQ_INCLUDE_TRYBOTS=master.client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot

Review-Url: https://codereview.chromium.org/2184753002
src/core/SkHalf.h
src/core/SkNx.h
src/core/SkRasterPipelineBlitter.cpp
src/opts/SkNx_neon.h
src/opts/SkNx_sse.h