Expand _01 half<->float limitation to _finite. Simplify.

    It's become clear we need to sometimes deal with values <0 or >1.
    I'm not yet convinced we care about NaN or +-inf.

    We had some fairly clever tricks and optimizations here for NEON
    and SSE.  I've thrown them out in favor of a single implementation.
    If we find the specializations mattered, we can certainly figure out
    how to extend them to this new range/domain.

    This happens to add a vectorized float -> half for ARMv7, which was
    missing from the _01 version.  (The SSE strategy was not portable to
    platforms that flush denorm floats to zero.)

    I've tested the full float range for FloatToHalf on my desktop and a 5x.

BUG=skia:
GOLD_TRYBOT_URL= https://gold.skia.org/search?issue=2145663003
CQ_INCLUDE_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot;master.client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot

Review-Url: https://codereview.chromium.org/2145663003

1 files changed, 1 insertions, 1 deletions

diff --git a/src/core/SkSpanProcs.cpp b/src/core/SkSpanProcs.cpp
index dddf7419e2..87dcbc0ee7 100644
--- a/src/core/SkSpanProcs.cpp
+++ b/src/core/SkSpanProcs.cpp
@@ -42,7 +42,7 @@ static void load_f16(const SkPixmap& src, int x, int y, SkPM4f span[], int count
     SkASSERT(src.addr64(x + count - 1, y));
 
     for (int i = 0; i < count; ++i) {
-        SkHalfToFloat_01(addr[i]).store(span[i].fVec);
+        SkHalfToFloat_finite(addr[i]).store(span[i].fVec);
     }
 }