// Auto-generated file. Do not edit!
//   Template: src/f32-gemm/1x8-aarch64-neonfma-ld64.S.in
//   Generator: tools/xngen
//
// Copyright 2020 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 <xnnpack/assembly.h>

# void xnn_f32_gemminc_minmax_ukernel_1x8__aarch64_neonfma_ld64(
#     size_t mr,                (x0) - unused.  mr = 1
#     size_t nc,                x1
#     size_t kc,                x2 / x0
#     const uint8_t*restrict a, x3
#     size_t a_stride,          (x4) - unused
#     const void*restrict w,    x5
#     uint8_t*restrict c,       x6
#     size_t cm_stride,         (x7) - unused
#     size_t cn_stride,         [sp] -> x14
#     const float*restrict acc,  [sp + 8] -> x15
#     const union xnn_f32_minmax_params params[restrict XNN_MIN_ELEMENTS(1)])  [sp + 16] -> (x8)

# d8-d15, x19-x30 need to be preserved if used. x18 is reserved by the OS.

# A pointer
# x3  a0

# C pointer
# x6  c0

# Clamp v4 v5

BEGIN_FUNCTION xnn_f32_gemminc_minmax_ukernel_1x8__aarch64_neonfma_ld64

        # Load cn_stride, acc
        LDP     x14, x15, [sp]
        # Load params pointer
        LDR     x8, [sp, 16]

        # Load min/max values
        LD2R    {v4.4s, v5.4s}, [x8]
0:
        # Load initial accumulators
        LDP     q16, q17, [x15], 32

        MOVI    v18.4s, 0               // second set of C for pipelining FMLA
        MOVI    v19.4s, 0

        # Is there at least 2 floats (8 bytes)
        SUBS    x0, x2, 8               // k = kc - 8

        B.LO    3f

        # Main loop - 2 floats of A (8 bytes)
1:
        LDR     d0, [x3], 8
        LDP     q20, q21, [x5], 32
        LDP     q22, q23, [x5], 32
        FMLA    v16.4s, v20.4s, v0.s[0]
        FMLA    v17.4s, v21.4s, v0.s[0]
        SUBS    x0, x0, 8
        FMLA    v18.4s, v22.4s, v0.s[1]
        FMLA    v19.4s, v23.4s, v0.s[1]
        B.HS    1b

        # Is there a remainder?- 1 float of A (4 bytes)
        TBNZ    x0, 2, 3f

2:
        FADD    v16.4s, v16.4s, v18.4s
        FADD    v17.4s, v17.4s, v19.4s
        SUBS    x1, x1, 8

        # Clamp
        FMAX    v16.4s, v16.4s, v4.4s
        FMAX    v17.4s, v17.4s, v4.4s
        FMIN    v16.4s, v16.4s, v5.4s
        FMIN    v17.4s, v17.4s, v5.4s

        # Store full 1 x 8
        B.LO    4f

        STP     q16, q17, [x6]
        ADD     x6, x6, x14

        SUB     x3,  x3, x2             // a0 -= kc

        B.HI    0b

        RET

3:
        # Remainder- 1 float of A (4 bytes)
        LDP     q20, q21, [x5], 32
        LDR     s0, [x3], 4
        FMLA    v16.4s, v20.4s, v0.s[0]
        FMLA    v17.4s, v21.4s, v0.s[0]
        B       2b

        # Store odd channels
4:
        TBZ     x1, 2, 5f
        STR     q16, [x6], 16
        MOV     v16.16b, v17.16b

5:
        TBZ     x1, 1, 6f
        STR     d16, [x6], 8
        DUP     d16, v16.d[1]

6:
        TBZ     x1, 0, 7f
        STR     s16, [x6]
7:
        RET

END_FUNCTION xnn_f32_gemminc_minmax_ukernel_1x8__aarch64_neonfma_ld64

#ifdef __ELF__
.section ".note.GNU-stack","",%progbits
#endif