/src/libjxl/lib/jxl/simd_util-inl.h

Source
// Copyright (c) the JPEG XL Project Authors. All rights reserved.
//
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

// Misc utilities for SIMD operations

#if defined(LIB_JXL_SIMD_UTIL_INL_H_) == defined(HWY_TARGET_TOGGLE)
#ifdef LIB_JXL_SIMD_UTIL_INL_H_
#undef LIB_JXL_SIMD_UTIL_INL_H_
#else
#define LIB_JXL_SIMD_UTIL_INL_H_
#endif

#include <hwy/highway.h>

#include "lib/jxl/base/compiler_specific.h"

HWY_BEFORE_NAMESPACE();
namespace jxl {
namespace HWY_NAMESPACE {

#if HWY_CAP_GE512
using hwy::HWY_NAMESPACE::Half;
using hwy::HWY_NAMESPACE::Vec;
template <size_t i, class DF, class V>
HWY_INLINE Vec<Half<Half<DF>>> Quarter(const DF df, V v) {
  using HF = Half<DF>;
  using HHF = Half<HF>;
  auto half = i >= 2 ? UpperHalf(HF(), v) : LowerHalf(HF(), v);
  return i & 1 ? UpperHalf(HHF(), half) : LowerHalf(HHF(), half);
}

template <class DF, class V>
HWY_INLINE Vec<DF> Concat4(const DF df, V v0, V v1, V v2, V v3) {
  using HF = Half<DF>;
  return Combine(DF(), Combine(HF(), v3, v2), Combine(HF(), v1, v0));
}

#endif

// Stores v0[0], v1[0], v0[1], v1[1], ... to mem, in this order. Mem must be
// aligned.
template <class DF, class V, typename T>
void StoreInterleaved(const DF df, V v0, V v1, T* mem) {
  static_assert(sizeof(T) == 4, "only use StoreInterleaved for 4-byte types");
#if HWY_TARGET == HWY_SCALAR
  Store(v0, df, mem);
  Store(v1, df, mem + 1);
#elif !HWY_CAP_GE256
  Store(InterleaveLower(df, v0, v1), df, mem);
  Store(InterleaveUpper(df, v0, v1), df, mem + Lanes(df));
#else
  if (!HWY_CAP_GE512 || Lanes(df) == 8) {
    auto t0 = InterleaveLower(df, v0, v1);
    auto t1 = InterleaveUpper(df, v0, v1);
    Store(ConcatLowerLower(df, t1, t0), df, mem);
    Store(ConcatUpperUpper(df, t1, t0), df, mem + Lanes(df));
  } else {
#if HWY_CAP_GE512
    auto t0 = InterleaveLower(df, v0, v1);
    auto t1 = InterleaveUpper(df, v0, v1);
    Store(Concat4(df, Quarter<0>(df, t0), Quarter<0>(df, t1),
                  Quarter<1>(df, t0), Quarter<1>(df, t1)),
          df, mem);
    Store(Concat4(df, Quarter<2>(df, t0), Quarter<2>(df, t1),
                  Quarter<3>(df, t0), Quarter<3>(df, t1)),
          df, mem + Lanes(df));
#endif
  }
#endif
}

// Stores v0[0], v1[0], v2[0], v3[0], v0[1] ... to mem, in this order. Mem must
// be aligned.
template <class DF, class V, typename T>
void StoreInterleaved(const DF df, V v0, V v1, V v2, V v3, T* mem) {
  static_assert(sizeof(T) == 4, "only use StoreInterleaved for 4-byte types");
#if HWY_TARGET == HWY_SCALAR
  Store(v0, df, mem);
  Store(v1, df, mem + 1);
  Store(v2, df, mem + 2);
  Store(v3, df, mem + 3);
#elif !HWY_CAP_GE256
  auto t0 = InterleaveLower(df, v0, v2);
  auto t1 = InterleaveLower(df, v1, v3);
  auto t2 = InterleaveUpper(df, v0, v2);
  auto t3 = InterleaveUpper(df, v1, v3);
  Store(InterleaveLower(df, t0, t1), df, mem);
  Store(InterleaveUpper(df, t0, t1), df, mem + Lanes(df));
  Store(InterleaveLower(df, t2, t3), df, mem + 2 * Lanes(df));
  Store(InterleaveUpper(df, t2, t3), df, mem + 3 * Lanes(df));
#elif !HWY_CAP_GE512
  auto t0 = InterleaveLower(df, v0, v2);
  auto t1 = InterleaveLower(df, v1, v3);
  auto t2 = InterleaveUpper(df, v0, v2);
  auto t3 = InterleaveUpper(df, v1, v3);

  auto m0 = InterleaveLower(df, t0, t1);
  auto m1 = InterleaveUpper(df, t0, t1);
  auto m2 = InterleaveLower(df, t2, t3);
  auto m3 = InterleaveUpper(df, t2, t3);

  Store(ConcatLowerLower(df, m1, m0), df, mem);
  Store(ConcatLowerLower(df, m3, m2), df, mem + Lanes(df));
  Store(ConcatUpperUpper(df, m1, m0), df, mem + 2 * Lanes(df));
  Store(ConcatUpperUpper(df, m3, m2), df, mem + 3 * Lanes(df));
#else
  auto t0 = InterleaveLower(df, v0, v2);
  auto t1 = InterleaveLower(df, v1, v3);
  auto t2 = InterleaveUpper(df, v0, v2);
  auto t3 = InterleaveUpper(df, v1, v3);

  auto m0 = InterleaveLower(df, t0, t1);
  auto m1 = InterleaveUpper(df, t0, t1);
  auto m2 = InterleaveLower(df, t2, t3);
  auto m3 = InterleaveUpper(df, t2, t3);

  Store(Concat4(df, Quarter<0>(df, m0), Quarter<0>(df, m1), Quarter<0>(df, m2),
                Quarter<0>(df, m3)),
        df, mem);
  Store(Concat4(df, Quarter<1>(df, m0), Quarter<1>(df, m1), Quarter<1>(df, m2),
                Quarter<1>(df, m3)),
        df, mem + Lanes(df));
  Store(Concat4(df, Quarter<2>(df, m0), Quarter<2>(df, m1), Quarter<2>(df, m2),
                Quarter<2>(df, m3)),
        df, mem + 2 * Lanes(df));
  Store(Concat4(df, Quarter<3>(df, m0), Quarter<3>(df, m1), Quarter<3>(df, m2),
                Quarter<3>(df, m3)),
        df, mem + 3 * Lanes(df));
#endif
}

// Stores v0[0], v1[0], v2[0], v3[0], v4[0], v5[0], v6[0], v7[0], v0[1] ... to
// mem, in this order. Mem must be aligned.
template <class DF, class V>
void StoreInterleaved(const DF df, V v0, V v1, V v2, V v3, V v4, V v5, V v6,
                      V v7, float* mem) {
#if HWY_TARGET == HWY_SCALAR
  Store(v0, df, mem);
  Store(v1, df, mem + 1);
  Store(v2, df, mem + 2);
  Store(v3, df, mem + 3);
  Store(v4, df, mem + 4);
  Store(v5, df, mem + 5);
  Store(v6, df, mem + 6);
  Store(v7, df, mem + 7);
#elif !HWY_CAP_GE256
  auto t0 = InterleaveLower(df, v0, v4);
  auto t1 = InterleaveLower(df, v1, v5);
  auto t2 = InterleaveLower(df, v2, v6);
  auto t3 = InterleaveLower(df, v3, v7);
  auto t4 = InterleaveUpper(df, v0, v4);
  auto t5 = InterleaveUpper(df, v1, v5);
  auto t6 = InterleaveUpper(df, v2, v6);
  auto t7 = InterleaveUpper(df, v3, v7);

  auto w0 = InterleaveLower(df, t0, t2);
  auto w1 = InterleaveLower(df, t1, t3);
  auto w2 = InterleaveUpper(df, t0, t2);
  auto w3 = InterleaveUpper(df, t1, t3);
  auto w4 = InterleaveLower(df, t4, t6);
  auto w5 = InterleaveLower(df, t5, t7);
  auto w6 = InterleaveUpper(df, t4, t6);
  auto w7 = InterleaveUpper(df, t5, t7);

  Store(InterleaveLower(df, w0, w1), df, mem);
  Store(InterleaveUpper(df, w0, w1), df, mem + Lanes(df));
  Store(InterleaveLower(df, w2, w3), df, mem + 2 * Lanes(df));
  Store(InterleaveUpper(df, w2, w3), df, mem + 3 * Lanes(df));
  Store(InterleaveLower(df, w4, w5), df, mem + 4 * Lanes(df));
  Store(InterleaveUpper(df, w4, w5), df, mem + 5 * Lanes(df));
  Store(InterleaveLower(df, w6, w7), df, mem + 6 * Lanes(df));
  Store(InterleaveUpper(df, w6, w7), df, mem + 7 * Lanes(df));
#elif !HWY_CAP_GE512
  auto t0 = InterleaveLower(df, v0, v4);
  auto t1 = InterleaveLower(df, v1, v5);
  auto t2 = InterleaveLower(df, v2, v6);
  auto t3 = InterleaveLower(df, v3, v7);
  auto t4 = InterleaveUpper(df, v0, v4);
  auto t5 = InterleaveUpper(df, v1, v5);
  auto t6 = InterleaveUpper(df, v2, v6);
  auto t7 = InterleaveUpper(df, v3, v7);

  auto w0 = InterleaveLower(df, t0, t2);
  auto w1 = InterleaveLower(df, t1, t3);
  auto w2 = InterleaveUpper(df, t0, t2);
  auto w3 = InterleaveUpper(df, t1, t3);
  auto w4 = InterleaveLower(df, t4, t6);
  auto w5 = InterleaveLower(df, t5, t7);
  auto w6 = InterleaveUpper(df, t4, t6);
  auto w7 = InterleaveUpper(df, t5, t7);

  auto m0 = InterleaveLower(df, w0, w1);
  auto m1 = InterleaveUpper(df, w0, w1);
  auto m2 = InterleaveLower(df, w2, w3);
  auto m3 = InterleaveUpper(df, w2, w3);
  auto m4 = InterleaveLower(df, w4, w5);
  auto m5 = InterleaveUpper(df, w4, w5);
  auto m6 = InterleaveLower(df, w6, w7);
  auto m7 = InterleaveUpper(df, w6, w7);

  Store(ConcatLowerLower(df, m1, m0), df, mem);
  Store(ConcatLowerLower(df, m3, m2), df, mem + Lanes(df));
  Store(ConcatLowerLower(df, m5, m4), df, mem + 2 * Lanes(df));
  Store(ConcatLowerLower(df, m7, m6), df, mem + 3 * Lanes(df));
  Store(ConcatUpperUpper(df, m1, m0), df, mem + 4 * Lanes(df));
  Store(ConcatUpperUpper(df, m3, m2), df, mem + 5 * Lanes(df));
  Store(ConcatUpperUpper(df, m5, m4), df, mem + 6 * Lanes(df));
  Store(ConcatUpperUpper(df, m7, m6), df, mem + 7 * Lanes(df));
#else
  auto t0 = InterleaveLower(df, v0, v4);
  auto t1 = InterleaveLower(df, v1, v5);
  auto t2 = InterleaveLower(df, v2, v6);
  auto t3 = InterleaveLower(df, v3, v7);
  auto t4 = InterleaveUpper(df, v0, v4);
  auto t5 = InterleaveUpper(df, v1, v5);
  auto t6 = InterleaveUpper(df, v2, v6);
  auto t7 = InterleaveUpper(df, v3, v7);

  auto w0 = InterleaveLower(df, t0, t2);
  auto w1 = InterleaveLower(df, t1, t3);
  auto w2 = InterleaveUpper(df, t0, t2);
  auto w3 = InterleaveUpper(df, t1, t3);
  auto w4 = InterleaveLower(df, t4, t6);
  auto w5 = InterleaveLower(df, t5, t7);
  auto w6 = InterleaveUpper(df, t4, t6);
  auto w7 = InterleaveUpper(df, t5, t7);

  auto m0 = InterleaveLower(df, w0, w1);
  auto m1 = InterleaveUpper(df, w0, w1);
  auto m2 = InterleaveLower(df, w2, w3);
  auto m3 = InterleaveUpper(df, w2, w3);
  auto m4 = InterleaveLower(df, w4, w5);
  auto m5 = InterleaveUpper(df, w4, w5);
  auto m6 = InterleaveLower(df, w6, w7);
  auto m7 = InterleaveUpper(df, w6, w7);

  Store(Concat4(df, Quarter<0>(df, m0), Quarter<0>(df, m1), Quarter<0>(df, m2),
                Quarter<0>(df, m3)),
        df, mem);
  Store(Concat4(df, Quarter<0>(df, m4), Quarter<0>(df, m5), Quarter<0>(df, m6),
                Quarter<0>(df, m7)),
        df, mem + Lanes(df));
  Store(Concat4(df, Quarter<1>(df, m0), Quarter<1>(df, m1), Quarter<1>(df, m2),
                Quarter<1>(df, m3)),
        df, mem + 2 * Lanes(df));
  Store(Concat4(df, Quarter<1>(df, m4), Quarter<1>(df, m5), Quarter<1>(df, m6),
                Quarter<1>(df, m7)),
        df, mem + 3 * Lanes(df));
  Store(Concat4(df, Quarter<2>(df, m0), Quarter<2>(df, m1), Quarter<2>(df, m2),
                Quarter<2>(df, m3)),
        df, mem + 4 * Lanes(df));
  Store(Concat4(df, Quarter<2>(df, m4), Quarter<2>(df, m5), Quarter<2>(df, m6),
                Quarter<2>(df, m7)),
        df, mem + 5 * Lanes(df));
  Store(Concat4(df, Quarter<3>(df, m0), Quarter<3>(df, m1), Quarter<3>(df, m2),
                Quarter<3>(df, m3)),
        df, mem + 6 * Lanes(df));
  Store(Concat4(df, Quarter<3>(df, m4), Quarter<3>(df, m5), Quarter<3>(df, m6),
                Quarter<3>(df, m7)),
        df, mem + 7 * Lanes(df));
#endif
}

#if HWY_CAP_GE256
JXL_INLINE void Transpose8x8Block(const int32_t* JXL_RESTRICT from,
                                  int32_t* JXL_RESTRICT to, size_t fromstride) {
  const HWY_CAPPED(int32_t, 8) d;
  auto i0 = Load(d, from);
  auto i1 = Load(d, from + 1 * fromstride);
  auto i2 = Load(d, from + 2 * fromstride);
  auto i3 = Load(d, from + 3 * fromstride);
  auto i4 = Load(d, from + 4 * fromstride);
  auto i5 = Load(d, from + 5 * fromstride);
  auto i6 = Load(d, from + 6 * fromstride);
  auto i7 = Load(d, from + 7 * fromstride);

  const auto q0 = InterleaveLower(d, i0, i2);
  const auto q1 = InterleaveLower(d, i1, i3);
  const auto q2 = InterleaveUpper(d, i0, i2);
  const auto q3 = InterleaveUpper(d, i1, i3);
  const auto q4 = InterleaveLower(d, i4, i6);
  const auto q5 = InterleaveLower(d, i5, i7);
  const auto q6 = InterleaveUpper(d, i4, i6);
  const auto q7 = InterleaveUpper(d, i5, i7);

  const auto r0 = InterleaveLower(d, q0, q1);
  const auto r1 = InterleaveUpper(d, q0, q1);
  const auto r2 = InterleaveLower(d, q2, q3);
  const auto r3 = InterleaveUpper(d, q2, q3);
  const auto r4 = InterleaveLower(d, q4, q5);
  const auto r5 = InterleaveUpper(d, q4, q5);
  const auto r6 = InterleaveLower(d, q6, q7);
  const auto r7 = InterleaveUpper(d, q6, q7);

  i0 = ConcatLowerLower(d, r4, r0);
  i1 = ConcatLowerLower(d, r5, r1);
  i2 = ConcatLowerLower(d, r6, r2);
  i3 = ConcatLowerLower(d, r7, r3);
  i4 = ConcatUpperUpper(d, r4, r0);
  i5 = ConcatUpperUpper(d, r5, r1);
  i6 = ConcatUpperUpper(d, r6, r2);
  i7 = ConcatUpperUpper(d, r7, r3);

  Store(i0, d, to);
  Store(i1, d, to + 1 * 8);
  Store(i2, d, to + 2 * 8);
  Store(i3, d, to + 3 * 8);
  Store(i4, d, to + 4 * 8);
  Store(i5, d, to + 5 * 8);
  Store(i6, d, to + 6 * 8);
  Store(i7, d, to + 7 * 8);
}
#elif HWY_TARGET != HWY_SCALAR
JXL_INLINE void Transpose8x8Block(const int32_t* JXL_RESTRICT from,
                                  int32_t* JXL_RESTRICT to, size_t fromstride) {
  const HWY_CAPPED(int32_t, 4) d;
  for (size_t n = 0; n < 8; n += 4) {
    for (size_t m = 0; m < 8; m += 4) {
      auto p0 = Load(d, from + n * fromstride + m);
      auto p1 = Load(d, from + (n + 1) * fromstride + m);
      auto p2 = Load(d, from + (n + 2) * fromstride + m);
      auto p3 = Load(d, from + (n + 3) * fromstride + m);
      const auto q0 = InterleaveLower(d, p0, p2);
      const auto q1 = InterleaveLower(d, p1, p3);
      const auto q2 = InterleaveUpper(d, p0, p2);
      const auto q3 = InterleaveUpper(d, p1, p3);

      const auto r0 = InterleaveLower(d, q0, q1);
      const auto r1 = InterleaveUpper(d, q0, q1);
      const auto r2 = InterleaveLower(d, q2, q3);
      const auto r3 = InterleaveUpper(d, q2, q3);
      Store(r0, d, to + m * 8 + n);
      Store(r1, d, to + (1 + m) * 8 + n);
      Store(r2, d, to + (2 + m) * 8 + n);
      Store(r3, d, to + (3 + m) * 8 + n);
    }
  }
}

#endif

// NOLINTNEXTLINE(google-readability-namespace-comments)
}  // namespace HWY_NAMESPACE
}  // namespace jxl
HWY_AFTER_NAMESPACE();

#endif  // LIB_JXL_SIMD_UTIL_INL_H_

Coverage Report

Created: 2025-06-22 08:04

Line	Count	Source
1		// Copyright (c) the JPEG XL Project Authors. All rights reserved.
2		//
3		// Use of this source code is governed by a BSD-style
4		// license that can be found in the LICENSE file.
5
6		// Misc utilities for SIMD operations
7
8		#if defined(LIB_JXL_SIMD_UTIL_INL_H_) == defined(HWY_TARGET_TOGGLE)
9		#ifdef LIB_JXL_SIMD_UTIL_INL_H_
10		#undef LIB_JXL_SIMD_UTIL_INL_H_
11		#else
12		#define LIB_JXL_SIMD_UTIL_INL_H_
13		#endif
14
15		#include <hwy/highway.h>
16
17		#include "lib/jxl/base/compiler_specific.h"
18
19		HWY_BEFORE_NAMESPACE();
20		namespace jxl {
21		namespace HWY_NAMESPACE {
22
23		#if HWY_CAP_GE512
24		using hwy::HWY_NAMESPACE::Half;
25		using hwy::HWY_NAMESPACE::Vec;
26		template <size_t i, class DF, class V>
27		HWY_INLINE Vec<Half<Half<DF>>> Quarter(const DF df, V v) {
28		using HF = Half<DF>;
29		using HHF = Half<HF>;
30		auto half = i >= 2 ? UpperHalf(HF(), v) : LowerHalf(HF(), v);
31		return i & 1 ? UpperHalf(HHF(), half) : LowerHalf(HHF(), half);
32		}
33
34		template <class DF, class V>
35		HWY_INLINE Vec<DF> Concat4(const DF df, V v0, V v1, V v2, V v3) {
36		using HF = Half<DF>;
37		return Combine(DF(), Combine(HF(), v3, v2), Combine(HF(), v1, v0));
38		}
39
40		#endif
41
42		// Stores v0[0], v1[0], v0[1], v1[1], ... to mem, in this order. Mem must be
43		// aligned.
44		template <class DF, class V, typename T>
45	191M	void StoreInterleaved(const DF df, V v0, V v1, T* mem) {
46	191M	static_assert(sizeof(T) == 4, "only use StoreInterleaved for 4-byte types");
47	191M	#if HWY_TARGET == HWY_SCALAR
48	191M	Store(v0, df, mem);
49	191M	Store(v1, df, mem + 1);
50		#elif !HWY_CAP_GE256
51		Store(InterleaveLower(df, v0, v1), df, mem);
52		Store(InterleaveUpper(df, v0, v1), df, mem + Lanes(df));
53		#else
54		if (!HWY_CAP_GE512 \|\| Lanes(df) == 8) {
55		auto t0 = InterleaveLower(df, v0, v1);
56		auto t1 = InterleaveUpper(df, v0, v1);
57		Store(ConcatLowerLower(df, t1, t0), df, mem);
58		Store(ConcatUpperUpper(df, t1, t0), df, mem + Lanes(df));
59		} else {
60		#if HWY_CAP_GE512
61		auto t0 = InterleaveLower(df, v0, v1);
62		auto t1 = InterleaveUpper(df, v0, v1);
63		Store(Concat4(df, Quarter<0>(df, t0), Quarter<0>(df, t1),
64		Quarter<1>(df, t0), Quarter<1>(df, t1)),
65		df, mem);
66		Store(Concat4(df, Quarter<2>(df, t0), Quarter<2>(df, t1),
67		Quarter<3>(df, t0), Quarter<3>(df, t1)),
68		df, mem + Lanes(df));
69		#endif
70		}
71		#endif
72	191M	}
73
74		// Stores v0[0], v1[0], v2[0], v3[0], v0[1] ... to mem, in this order. Mem must
75		// be aligned.
76		template <class DF, class V, typename T>
77	93.9M	void StoreInterleaved(const DF df, V v0, V v1, V v2, V v3, T* mem) {
78	93.9M	static_assert(sizeof(T) == 4, "only use StoreInterleaved for 4-byte types");
79	93.9M	#if HWY_TARGET == HWY_SCALAR
80	93.9M	Store(v0, df, mem);
81	93.9M	Store(v1, df, mem + 1);
82	93.9M	Store(v2, df, mem + 2);
83	93.9M	Store(v3, df, mem + 3);
84		#elif !HWY_CAP_GE256
85		auto t0 = InterleaveLower(df, v0, v2);
86		auto t1 = InterleaveLower(df, v1, v3);
87		auto t2 = InterleaveUpper(df, v0, v2);
88		auto t3 = InterleaveUpper(df, v1, v3);
89		Store(InterleaveLower(df, t0, t1), df, mem);
90		Store(InterleaveUpper(df, t0, t1), df, mem + Lanes(df));
91		Store(InterleaveLower(df, t2, t3), df, mem + 2 * Lanes(df));
92		Store(InterleaveUpper(df, t2, t3), df, mem + 3 * Lanes(df));
93		#elif !HWY_CAP_GE512
94		auto t0 = InterleaveLower(df, v0, v2);
95		auto t1 = InterleaveLower(df, v1, v3);
96		auto t2 = InterleaveUpper(df, v0, v2);
97		auto t3 = InterleaveUpper(df, v1, v3);
98
99		auto m0 = InterleaveLower(df, t0, t1);
100		auto m1 = InterleaveUpper(df, t0, t1);
101		auto m2 = InterleaveLower(df, t2, t3);
102		auto m3 = InterleaveUpper(df, t2, t3);
103
104		Store(ConcatLowerLower(df, m1, m0), df, mem);
105		Store(ConcatLowerLower(df, m3, m2), df, mem + Lanes(df));
106		Store(ConcatUpperUpper(df, m1, m0), df, mem + 2 * Lanes(df));
107		Store(ConcatUpperUpper(df, m3, m2), df, mem + 3 * Lanes(df));
108		#else
109		auto t0 = InterleaveLower(df, v0, v2);
110		auto t1 = InterleaveLower(df, v1, v3);
111		auto t2 = InterleaveUpper(df, v0, v2);
112		auto t3 = InterleaveUpper(df, v1, v3);
113
114		auto m0 = InterleaveLower(df, t0, t1);
115		auto m1 = InterleaveUpper(df, t0, t1);
116		auto m2 = InterleaveLower(df, t2, t3);
117		auto m3 = InterleaveUpper(df, t2, t3);
118
119		Store(Concat4(df, Quarter<0>(df, m0), Quarter<0>(df, m1), Quarter<0>(df, m2),
120		Quarter<0>(df, m3)),
121		df, mem);
122		Store(Concat4(df, Quarter<1>(df, m0), Quarter<1>(df, m1), Quarter<1>(df, m2),
123		Quarter<1>(df, m3)),
124		df, mem + Lanes(df));
125		Store(Concat4(df, Quarter<2>(df, m0), Quarter<2>(df, m1), Quarter<2>(df, m2),
126		Quarter<2>(df, m3)),
127		df, mem + 2 * Lanes(df));
128		Store(Concat4(df, Quarter<3>(df, m0), Quarter<3>(df, m1), Quarter<3>(df, m2),
129		Quarter<3>(df, m3)),
130		df, mem + 3 * Lanes(df));
131		#endif
132	93.9M	}
133
134		// Stores v0[0], v1[0], v2[0], v3[0], v4[0], v5[0], v6[0], v7[0], v0[1] ... to
135		// mem, in this order. Mem must be aligned.
136		template <class DF, class V>
137		void StoreInterleaved(const DF df, V v0, V v1, V v2, V v3, V v4, V v5, V v6,
138	86.2M	V v7, float* mem) {
139	86.2M	#if HWY_TARGET == HWY_SCALAR
140	86.2M	Store(v0, df, mem);
141	86.2M	Store(v1, df, mem + 1);
142	86.2M	Store(v2, df, mem + 2);
143	86.2M	Store(v3, df, mem + 3);
144	86.2M	Store(v4, df, mem + 4);
145	86.2M	Store(v5, df, mem + 5);
146	86.2M	Store(v6, df, mem + 6);
147	86.2M	Store(v7, df, mem + 7);
148		#elif !HWY_CAP_GE256
149		auto t0 = InterleaveLower(df, v0, v4);
150		auto t1 = InterleaveLower(df, v1, v5);
151		auto t2 = InterleaveLower(df, v2, v6);
152		auto t3 = InterleaveLower(df, v3, v7);
153		auto t4 = InterleaveUpper(df, v0, v4);
154		auto t5 = InterleaveUpper(df, v1, v5);
155		auto t6 = InterleaveUpper(df, v2, v6);
156		auto t7 = InterleaveUpper(df, v3, v7);
157
158		auto w0 = InterleaveLower(df, t0, t2);
159		auto w1 = InterleaveLower(df, t1, t3);
160		auto w2 = InterleaveUpper(df, t0, t2);
161		auto w3 = InterleaveUpper(df, t1, t3);
162		auto w4 = InterleaveLower(df, t4, t6);
163		auto w5 = InterleaveLower(df, t5, t7);
164		auto w6 = InterleaveUpper(df, t4, t6);
165		auto w7 = InterleaveUpper(df, t5, t7);
166
167		Store(InterleaveLower(df, w0, w1), df, mem);
168		Store(InterleaveUpper(df, w0, w1), df, mem + Lanes(df));
169		Store(InterleaveLower(df, w2, w3), df, mem + 2 * Lanes(df));
170		Store(InterleaveUpper(df, w2, w3), df, mem + 3 * Lanes(df));
171		Store(InterleaveLower(df, w4, w5), df, mem + 4 * Lanes(df));
172		Store(InterleaveUpper(df, w4, w5), df, mem + 5 * Lanes(df));
173		Store(InterleaveLower(df, w6, w7), df, mem + 6 * Lanes(df));
174		Store(InterleaveUpper(df, w6, w7), df, mem + 7 * Lanes(df));
175		#elif !HWY_CAP_GE512
176		auto t0 = InterleaveLower(df, v0, v4);
177		auto t1 = InterleaveLower(df, v1, v5);
178		auto t2 = InterleaveLower(df, v2, v6);
179		auto t3 = InterleaveLower(df, v3, v7);
180		auto t4 = InterleaveUpper(df, v0, v4);
181		auto t5 = InterleaveUpper(df, v1, v5);
182		auto t6 = InterleaveUpper(df, v2, v6);
183		auto t7 = InterleaveUpper(df, v3, v7);
184
185		auto w0 = InterleaveLower(df, t0, t2);
186		auto w1 = InterleaveLower(df, t1, t3);
187		auto w2 = InterleaveUpper(df, t0, t2);
188		auto w3 = InterleaveUpper(df, t1, t3);
189		auto w4 = InterleaveLower(df, t4, t6);
190		auto w5 = InterleaveLower(df, t5, t7);
191		auto w6 = InterleaveUpper(df, t4, t6);
192		auto w7 = InterleaveUpper(df, t5, t7);
193
194		auto m0 = InterleaveLower(df, w0, w1);
195		auto m1 = InterleaveUpper(df, w0, w1);
196		auto m2 = InterleaveLower(df, w2, w3);
197		auto m3 = InterleaveUpper(df, w2, w3);
198		auto m4 = InterleaveLower(df, w4, w5);
199		auto m5 = InterleaveUpper(df, w4, w5);
200		auto m6 = InterleaveLower(df, w6, w7);
201		auto m7 = InterleaveUpper(df, w6, w7);
202
203		Store(ConcatLowerLower(df, m1, m0), df, mem);
204		Store(ConcatLowerLower(df, m3, m2), df, mem + Lanes(df));
205		Store(ConcatLowerLower(df, m5, m4), df, mem + 2 * Lanes(df));
206		Store(ConcatLowerLower(df, m7, m6), df, mem + 3 * Lanes(df));
207		Store(ConcatUpperUpper(df, m1, m0), df, mem + 4 * Lanes(df));
208		Store(ConcatUpperUpper(df, m3, m2), df, mem + 5 * Lanes(df));
209		Store(ConcatUpperUpper(df, m5, m4), df, mem + 6 * Lanes(df));
210		Store(ConcatUpperUpper(df, m7, m6), df, mem + 7 * Lanes(df));
211		#else
212		auto t0 = InterleaveLower(df, v0, v4);
213		auto t1 = InterleaveLower(df, v1, v5);
214		auto t2 = InterleaveLower(df, v2, v6);
215		auto t3 = InterleaveLower(df, v3, v7);
216		auto t4 = InterleaveUpper(df, v0, v4);
217		auto t5 = InterleaveUpper(df, v1, v5);
218		auto t6 = InterleaveUpper(df, v2, v6);
219		auto t7 = InterleaveUpper(df, v3, v7);
220
221		auto w0 = InterleaveLower(df, t0, t2);
222		auto w1 = InterleaveLower(df, t1, t3);
223		auto w2 = InterleaveUpper(df, t0, t2);
224		auto w3 = InterleaveUpper(df, t1, t3);
225		auto w4 = InterleaveLower(df, t4, t6);
226		auto w5 = InterleaveLower(df, t5, t7);
227		auto w6 = InterleaveUpper(df, t4, t6);
228		auto w7 = InterleaveUpper(df, t5, t7);
229
230		auto m0 = InterleaveLower(df, w0, w1);
231		auto m1 = InterleaveUpper(df, w0, w1);
232		auto m2 = InterleaveLower(df, w2, w3);
233		auto m3 = InterleaveUpper(df, w2, w3);
234		auto m4 = InterleaveLower(df, w4, w5);
235		auto m5 = InterleaveUpper(df, w4, w5);
236		auto m6 = InterleaveLower(df, w6, w7);
237		auto m7 = InterleaveUpper(df, w6, w7);
238
239		Store(Concat4(df, Quarter<0>(df, m0), Quarter<0>(df, m1), Quarter<0>(df, m2),
240		Quarter<0>(df, m3)),
241		df, mem);
242		Store(Concat4(df, Quarter<0>(df, m4), Quarter<0>(df, m5), Quarter<0>(df, m6),
243		Quarter<0>(df, m7)),
244		df, mem + Lanes(df));
245		Store(Concat4(df, Quarter<1>(df, m0), Quarter<1>(df, m1), Quarter<1>(df, m2),
246		Quarter<1>(df, m3)),
247		df, mem + 2 * Lanes(df));
248		Store(Concat4(df, Quarter<1>(df, m4), Quarter<1>(df, m5), Quarter<1>(df, m6),
249		Quarter<1>(df, m7)),
250		df, mem + 3 * Lanes(df));
251		Store(Concat4(df, Quarter<2>(df, m0), Quarter<2>(df, m1), Quarter<2>(df, m2),
252		Quarter<2>(df, m3)),
253		df, mem + 4 * Lanes(df));
254		Store(Concat4(df, Quarter<2>(df, m4), Quarter<2>(df, m5), Quarter<2>(df, m6),
255		Quarter<2>(df, m7)),
256		df, mem + 5 * Lanes(df));
257		Store(Concat4(df, Quarter<3>(df, m0), Quarter<3>(df, m1), Quarter<3>(df, m2),
258		Quarter<3>(df, m3)),
259		df, mem + 6 * Lanes(df));
260		Store(Concat4(df, Quarter<3>(df, m4), Quarter<3>(df, m5), Quarter<3>(df, m6),
261		Quarter<3>(df, m7)),
262		df, mem + 7 * Lanes(df));
263		#endif
264	86.2M	}
265
266		#if HWY_CAP_GE256
267		JXL_INLINE void Transpose8x8Block(const int32_t* JXL_RESTRICT from,
268		int32_t* JXL_RESTRICT to, size_t fromstride) {
269		const HWY_CAPPED(int32_t, 8) d;
270		auto i0 = Load(d, from);
271		auto i1 = Load(d, from + 1 * fromstride);
272		auto i2 = Load(d, from + 2 * fromstride);
273		auto i3 = Load(d, from + 3 * fromstride);
274		auto i4 = Load(d, from + 4 * fromstride);
275		auto i5 = Load(d, from + 5 * fromstride);
276		auto i6 = Load(d, from + 6 * fromstride);
277		auto i7 = Load(d, from + 7 * fromstride);
278
279		const auto q0 = InterleaveLower(d, i0, i2);
280		const auto q1 = InterleaveLower(d, i1, i3);
281		const auto q2 = InterleaveUpper(d, i0, i2);
282		const auto q3 = InterleaveUpper(d, i1, i3);
283		const auto q4 = InterleaveLower(d, i4, i6);
284		const auto q5 = InterleaveLower(d, i5, i7);
285		const auto q6 = InterleaveUpper(d, i4, i6);
286		const auto q7 = InterleaveUpper(d, i5, i7);
287
288		const auto r0 = InterleaveLower(d, q0, q1);
289		const auto r1 = InterleaveUpper(d, q0, q1);
290		const auto r2 = InterleaveLower(d, q2, q3);
291		const auto r3 = InterleaveUpper(d, q2, q3);
292		const auto r4 = InterleaveLower(d, q4, q5);
293		const auto r5 = InterleaveUpper(d, q4, q5);
294		const auto r6 = InterleaveLower(d, q6, q7);
295		const auto r7 = InterleaveUpper(d, q6, q7);
296
297		i0 = ConcatLowerLower(d, r4, r0);
298		i1 = ConcatLowerLower(d, r5, r1);
299		i2 = ConcatLowerLower(d, r6, r2);
300		i3 = ConcatLowerLower(d, r7, r3);
301		i4 = ConcatUpperUpper(d, r4, r0);
302		i5 = ConcatUpperUpper(d, r5, r1);
303		i6 = ConcatUpperUpper(d, r6, r2);
304		i7 = ConcatUpperUpper(d, r7, r3);
305
306		Store(i0, d, to);
307		Store(i1, d, to + 1 * 8);
308		Store(i2, d, to + 2 * 8);
309		Store(i3, d, to + 3 * 8);
310		Store(i4, d, to + 4 * 8);
311		Store(i5, d, to + 5 * 8);
312		Store(i6, d, to + 6 * 8);
313		Store(i7, d, to + 7 * 8);
314		}
315		#elif HWY_TARGET != HWY_SCALAR
316		JXL_INLINE void Transpose8x8Block(const int32_t* JXL_RESTRICT from,
317		int32_t* JXL_RESTRICT to, size_t fromstride) {
318		const HWY_CAPPED(int32_t, 4) d;
319		for (size_t n = 0; n < 8; n += 4) {
320		for (size_t m = 0; m < 8; m += 4) {
321		auto p0 = Load(d, from + n * fromstride + m);
322		auto p1 = Load(d, from + (n + 1) * fromstride + m);
323		auto p2 = Load(d, from + (n + 2) * fromstride + m);
324		auto p3 = Load(d, from + (n + 3) * fromstride + m);
325		const auto q0 = InterleaveLower(d, p0, p2);
326		const auto q1 = InterleaveLower(d, p1, p3);
327		const auto q2 = InterleaveUpper(d, p0, p2);
328		const auto q3 = InterleaveUpper(d, p1, p3);
329
330		const auto r0 = InterleaveLower(d, q0, q1);
331		const auto r1 = InterleaveUpper(d, q0, q1);
332		const auto r2 = InterleaveLower(d, q2, q3);
333		const auto r3 = InterleaveUpper(d, q2, q3);
334		Store(r0, d, to + m * 8 + n);
335		Store(r1, d, to + (1 + m) * 8 + n);
336		Store(r2, d, to + (2 + m) * 8 + n);
337		Store(r3, d, to + (3 + m) * 8 + n);
338		}
339		}
340		}
341
342		#endif
343
344		// NOLINTNEXTLINE(google-readability-namespace-comments)
345		} // namespace HWY_NAMESPACE
346		} // namespace jxl
347		HWY_AFTER_NAMESPACE();
348
349		#endif // LIB_JXL_SIMD_UTIL_INL_H_