// clang-format off

// Auto-generated file. Do not edit!

//   Template: src/f32-gemm/avx-broadcast.c.in

//   Generator: tools/xngen

//

// Copyright 2019 Google LLC

//

// This source code is licensed under the BSD-style license found in the

// LICENSE file in the root directory of this source tree.

#include <assert.h>

#include <stddef.h>

#include <stdint.h>

#include <immintrin.h>

#include "src/xnnpack/common.h"

#include "src/xnnpack/gemm.h"

#include "src/xnnpack/microparams.h"

void xnn_f32_gemm_minmax_ukernel_1x8__fma3_broadcast(

    size_t mr,

    size_t nc,

    size_t kc,

    const float* restrict a,

    size_t a_stride,

    const float* restrict w,

    float* restrict c,

    size_t cm_stride,

    size_t cn_stride,

    const struct xnn_f32_minmax_params* restrict params)

{

  assert(mr != 0);

  assert(mr <= 1);

  assert(nc != 0);

  assert(kc != 0);

  assert(kc % sizeof(float) == 0);

  assert(a != NULL);

  assert(w != NULL);

  assert(c != NULL);

  const float* a0 = a;

  float* c0 = c;

  const __m256 vmin = _mm256_set1_ps(params->scalar.min);

  const __m256 vmax = _mm256_set1_ps(params->scalar.max);

  XNN_FORCE_REALIZATION(vmin);

  XNN_FORCE_REALIZATION(vmax);

  do {

    __m256 vacc0x01234567 = _mm256_load_ps(w + 0);

    w += 8;

    size_t k = kc;

    do {

      const __m256 va0 = _mm256_broadcast_ss(a0);

      a0 += 1;

      const __m256 vb01234567 = _mm256_load_ps(w);

      w += 8;

      vacc0x01234567 = _mm256_fmadd_ps(va0, vb01234567, vacc0x01234567);

      k -= sizeof(float);

    } while (k != 0);

    vacc0x01234567 = _mm256_max_ps(vmin, vacc0x01234567);

    vacc0x01234567 = _mm256_min_ps(vmax, vacc0x01234567);

    if XNN_LIKELY(nc >= 8) {

      _mm256_storeu_ps(c0, vacc0x01234567);

      c0 = (float*) ((uintptr_t) c0 + cn_stride);

      a0 = (const float*) ((uintptr_t) a0 - kc);

      nc -= 8;

    } else {

      __m128 vacc0x0123 = _mm256_castps256_ps128(vacc0x01234567);

      if (nc & 4) {

        _mm_storeu_ps(c0, vacc0x0123);

        vacc0x0123 = _mm256_extractf128_ps(vacc0x01234567, 1);

        c0 += 4;

      }

      if (nc & 2) {

        _mm_storel_pi((__m64*) c0, vacc0x0123);

        vacc0x0123 = _mm_movehl_ps(vacc0x0123, vacc0x0123);

        c0 += 2;

      }

      if (nc & 1) {

        _mm_store_ss(c0, vacc0x0123);

      }

      nc = 0;

    }

  } while (nc != 0);

}