swr/rast: SIMD16 FE - fix/use SIMD16 calcDeterminantIntVertical()

Stop double pumping the SIMD8 version.

Reviewed-by: Bruce Cherniak <[email protected]>

2 files changed, 46 insertions, 0 deletions

diff --git a/src/gallium/drivers/swr/rasterizer/common/simd16intrin.h b/src/gallium/drivers/swr/rasterizer/common/simd16intrin.h
index 84585ffc8fc..e303ce59713 100644
--- a/src/gallium/drivers/swr/rasterizer/common/simd16intrin.h
+++ b/src/gallium/drivers/swr/rasterizer/common/simd16intrin.h
@@ -770,6 +770,26 @@ INLINE simd16scalari SIMDAPI _simd16_cvtepu16_epi32(simdscalari a)
     return result;
 }
 
+INLINE simd16scalari SIMDAPI _simd16_cvtepu16_epi64(simdscalari a)
+{
+    simd16scalari result;
+
+    result.lo = _simd_cvtepu16_epi64(_mm256_extractf128_si256(a, 0));
+    result.hi = _simd_cvtepu16_epi64(_mm256_extractf128_si256(a, 1));
+
+    return result;
+}
+
+INLINE simd16scalari SIMDAPI _simd16_cvtepu32_epi64(simdscalari a)
+{
+    simd16scalari result;
+
+    result.lo = _simd_cvtepu32_epi64(_mm256_extractf128_si256(a, 0));
+    result.hi = _simd_cvtepu32_epi64(_mm256_extractf128_si256(a, 1));
+
+    return result;
+}
+
 SIMD16_EMU_AVX512_2(simd16scalari, _simd16_packus_epi16, _simd_packus_epi16)
 SIMD16_EMU_AVX512_2(simd16scalari, _simd16_packs_epi16, _simd_packs_epi16)
 SIMD16_EMU_AVX512_2(simd16scalari, _simd16_packus_epi32, _simd_packus_epi32)
@@ -1097,6 +1117,8 @@ INLINE simd16scalari SIMDAPI _simd16_cmpgt_epi8(simd16scalari a, simd16scalari b
 #define _simd16_cvtepu8_epi16           _mm512_cvtepu8_epi16
 #define _simd16_cvtepu8_epi32           _mm512_cvtepu8_epi32
 #define _simd16_cvtepu16_epi32          _mm512_cvtepu16_epi32
+#define _simd16_cvtepu16_epi64          _mm512_cvtepu16_epi64
+#define _simd16_cvtepu32_epi64          _mm512_cvtepu32_epi64
 #define _simd16_packus_epi16            _mm512_packus_epi16
 #define _simd16_packs_epi16             _mm512_packs_epi16
 #define _simd16_packus_epi32            _mm512_packus_epi32
diff --git a/src/gallium/drivers/swr/rasterizer/common/simdintrin.h b/src/gallium/drivers/swr/rasterizer/common/simdintrin.h
index 61c0c5461a3..ed6e56b5e26 100644
--- a/src/gallium/drivers/swr/rasterizer/common/simdintrin.h
+++ b/src/gallium/drivers/swr/rasterizer/common/simdintrin.h
@@ -456,6 +456,28 @@ __m256i _simd_cvtepu16_epi32(__m128i a)
 }
 
 INLINE
+__m256i _simd_cvtepu16_epi64(__m128i a)
+{
+    __m128i resultlo = _mm_cvtepu16_epi64(a);
+    __m128i resulthi = _mm_cvtepu16_epi64(_mm_srli_si128(a, 4));
+
+    __m256i result = _mm256_castsi128_si256(resultlo);
+
+    return _mm256_insertf128_si256(result, resulthi, 1);
+}
+
+INLINE
+__m256i _simd_cvtepu32_epi64(__m128i a)
+{
+    __m128i resultlo = _mm_cvtepu32_epi64(a);
+    __m128i resulthi = _mm_cvtepu32_epi64(_mm_srli_si128(a, 8));
+
+    __m256i result = _mm256_castsi128_si256(resultlo);
+
+    return _mm256_insertf128_si256(result, resulthi, 1);
+}
+
+INLINE
 __m256i _simd_packus_epi16(__m256i a, __m256i b)
 {
     __m128i alo = _mm256_extractf128_si256(a, 0);
@@ -582,6 +604,8 @@ __m256i _simd_packs_epi32(__m256i a, __m256i b)
 #define _simd_cvtepu8_epi16 _mm256_cvtepu8_epi16
 #define _simd_cvtepu8_epi32 _mm256_cvtepu8_epi32
 #define _simd_cvtepu16_epi32 _mm256_cvtepu16_epi32
+#define _simd_cvtepu16_epi64 _mm256_cvtepu16_epi64
+#define _simd_cvtepu32_epi64 _mm256_cvtepu32_epi64
 #define _simd_packus_epi16 _mm256_packus_epi16
 #define _simd_packs_epi16 _mm256_packs_epi16
 #define _simd_packus_epi32 _mm256_packus_epi32