diff options
author | Tim Rowley <[email protected]> | 2017-11-13 15:11:21 -0600 |
---|---|---|
committer | Tim Rowley <[email protected]> | 2017-11-14 11:39:02 -0600 |
commit | 439904847e9c2970494c18e8c47bd6c38c0ed8ab (patch) | |
tree | e13d8d9b6bb74b351c35b255822e0fbaf31f7d5e | |
parent | 0db36caa192b129cb4f22d152f82f38fcf6f06d4 (diff) |
swr/rast: Use gather instruction for i32gather_ps on simd16/avx512
Speed up avx512 platforms; fixes performance regression caused
by swithc to simdlib.
Reviewed-by: Bruce Cherniak <[email protected]>
Cc: [email protected]
-rw-r--r-- | src/gallium/drivers/swr/rasterizer/common/simdlib_512_avx512.inl | 12 |
1 files changed, 1 insertions, 11 deletions
diff --git a/src/gallium/drivers/swr/rasterizer/common/simdlib_512_avx512.inl b/src/gallium/drivers/swr/rasterizer/common/simdlib_512_avx512.inl index 95e4c319099..c13b9f616aa 100644 --- a/src/gallium/drivers/swr/rasterizer/common/simdlib_512_avx512.inl +++ b/src/gallium/drivers/swr/rasterizer/common/simdlib_512_avx512.inl @@ -484,17 +484,7 @@ SIMD_WRAPPER_2(unpacklo_ps); template<ScaleFactor ScaleT> static SIMDINLINE Float SIMDCALL i32gather_ps(float const* p, Integer idx) // return *(float*)(((int8*)p) + (idx * ScaleT)) { - uint32_t *pOffsets = (uint32_t*)&idx; - Float vResult; - float* pResult = (float*)&vResult; - for (uint32_t i = 0; i < SIMD_WIDTH; ++i) - { - uint32_t offset = pOffsets[i]; - offset = offset * static_cast<uint32_t>(ScaleT); - pResult[i] = *(float const*)(((uint8_t const*)p + offset)); - } - - return vResult; + return _mm512_i32gather_ps(idx, p, static_cast<int>(ScaleT)); } static SIMDINLINE Float SIMDCALL load1_ps(float const *p) // return *p (broadcast 1 value to all elements) |