// M256MaskzLzcntEpi64: Counts the number of leading zero bits in each packed
// 64-bit integer in 'a', and store the results in 'dst' using zeromask 'k'
// (elements are zeroed out when the corresponding mask bit is not set).
//
// FOR j := 0 to 3
// i := j*64
// IF k[j]
// tmp := 63
// dst[i+63:i] := 0
// DO WHILE (tmp >= 0 AND a[i+tmp] == 0)
// tmp := tmp - 1
// dst[i+63:i] := dst[i+63:i] + 1
// OD
// ELSE
// dst[i+63:i] := 0
// FI
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPLZCNTQ'. Intrinsic: '_mm256_maskz_lzcnt_epi64'.
// Requires AVX512CD.
func M256MaskzLzcntEpi64(k x86.Mmask8, a x86.M256i) (dst x86.M256i) {
return x86.M256i(m256MaskzLzcntEpi64(uint8(k), [32]byte(a)))
}
// M256BroadcastmwEpi32: Broadcast the low 16-bits from input mask 'k' to all
// 32-bit elements of 'dst'.
//
// FOR j := 0 to 7
// i := j*32
// dst[i+31:i] := ZeroExtend(k[15:0])
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPBROADCASTMW2D'. Intrinsic: '_mm256_broadcastmw_epi32'.
// Requires AVX512CD.
func M256BroadcastmwEpi32(k x86.Mmask16) (dst x86.M256i) {
return x86.M256i(m256BroadcastmwEpi32(uint16(k)))
}
// M256MaskLzcntEpi64: Counts the number of leading zero bits in each packed
// 64-bit integer in 'a', and store the results in 'dst' using writemask 'k'
// (elements are copied from 'src' when the corresponding mask bit is not set).
//
// FOR j := 0 to 3
// i := j*64
// IF k[j]
// tmp := 63
// dst[i+63:i] := 0
// DO WHILE (tmp >= 0 AND a[i+tmp] == 0)
// tmp := tmp - 1
// dst[i+63:i] := dst[i+63:i] + 1
// OD
// ELSE
// dst[i+63:i] := src[i+63:i]
// FI
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPLZCNTQ'. Intrinsic: '_mm256_mask_lzcnt_epi64'.
// Requires AVX512CD.
func M256MaskLzcntEpi64(src x86.M256i, k x86.Mmask8, a x86.M256i) (dst x86.M256i) {
return x86.M256i(m256MaskLzcntEpi64([32]byte(src), uint8(k), [32]byte(a)))
}
// M256LzcntEpi64: Counts the number of leading zero bits in each packed 64-bit
// integer in 'a', and store the results in 'dst'.
//
// FOR j := 0 to 3
// i := j*64
// tmp := 63
// dst[i+63:i] := 0
// DO WHILE (tmp >= 0 AND a[i+tmp] == 0)
// tmp := tmp - 1
// dst[i+63:i] := dst[i+63:i] + 1
// OD
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPLZCNTQ'. Intrinsic: '_mm256_lzcnt_epi64'.
// Requires AVX512CD.
func M256LzcntEpi64(a x86.M256i) (dst x86.M256i) {
return x86.M256i(m256LzcntEpi64([32]byte(a)))
}
// M256ConflictEpi64: Test each 64-bit element of 'a' for equality with all
// other elements in 'a' closer to the least significant bit. Each element's
// comparison forms a zero extended bit vector in 'dst'.
//
// FOR j := 0 to 3
// i := j*64
// FOR k := 0 to j-1
// m := k*64
// dst[i+k] := (a[i+63:i] == a[m+63:m]) ? 1 : 0
// ENDFOR
// dst[i+63:i+j] := 0
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPCONFLICTQ'. Intrinsic: '_mm256_conflict_epi64'.
// Requires AVX512CD.
func M256ConflictEpi64(a x86.M256i) (dst x86.M256i) {
return x86.M256i(m256ConflictEpi64([32]byte(a)))
}
// M256BroadcastmbEpi64: Broadcast the low 8-bits from input mask 'k' to all
// 64-bit elements of 'dst'.
//
// FOR j := 0 to 3
// i := j*64
// dst[i+63:i] := ZeroExtend(k[7:0])
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPBROADCASTMB2Q'. Intrinsic: '_mm256_broadcastmb_epi64'.
// Requires AVX512CD.
func M256BroadcastmbEpi64(k x86.Mmask8) (dst x86.M256i) {
return x86.M256i(m256BroadcastmbEpi64(uint8(k)))
}
// M256MaskzConflictEpi32: Test each 32-bit element of 'a' for equality with
// all other elements in 'a' closer to the least significant bit using zeromask
// 'k' (elements are zeroed out when the corresponding mask bit is not set).
// Each element's comparison forms a zero extended bit vector in 'dst'.
//
// FOR j := 0 to 7
// i := j*32
// IF k[i]
// FOR l := 0 to j-1
// m := l*32
// dst[i+l] := (a[i+31:i] == a[m+31:m]) ? 1 : 0
// ENDFOR
// dst[i+31:i+j] := 0
// ELSE
// dst[i+31:i] := 0
// FI
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPCONFLICTD'. Intrinsic: '_mm256_maskz_conflict_epi32'.
// Requires AVX512CD.
func M256MaskzConflictEpi32(k x86.Mmask8, a x86.M256i) (dst x86.M256i) {
return x86.M256i(m256MaskzConflictEpi32(uint8(k), [32]byte(a)))
}
// M256MaskConflictEpi32: Test each 32-bit element of 'a' for equality with all
// other elements in 'a' closer to the least significant bit using writemask
// 'k' (elements are copied from 'src' when the corresponding mask bit is not
// set). Each element's comparison forms a zero extended bit vector in 'dst'.
//
// FOR j := 0 to 7
// i := j*32
// IF k[i]
// FOR l := 0 to j-1
// m := l*32
// dst[i+l] := (a[i+31:i] == a[m+31:m]) ? 1 : 0
// ENDFOR
// dst[i+31:i+j] := 0
// ELSE
// dst[i+31:i] := src[i+31:i]
// FI
// ENDFOR
// dst[MAX:256] := 0
//
// Instruction: 'VPCONFLICTD'. Intrinsic: '_mm256_mask_conflict_epi32'.
// Requires AVX512CD.
func M256MaskConflictEpi32(src x86.M256i, k x86.Mmask8, a x86.M256i) (dst x86.M256i) {
return x86.M256i(m256MaskConflictEpi32([32]byte(src), uint8(k), [32]byte(a)))
}