// 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_f16_gemm${"inc" if INC else ""}_minmax_ukernel_1x8__aarch64_neonfp16arith_ld64(
#     size_t mr,                (x0) - unused.  mr = 1
#     size_t nc,                x1
#     size_t kc,                x2 / x0
#     const void*restrict a,    x3
#     size_t a_stride,          (x4) - unused
#     const void*restrict w,    x5
#     void*restrict c,          x6
#     size_t cm_stride,         (x7) - unused
#     size_t cn_stride,         [sp] -> x14
$if INC:
  #     const float*restrict acc,  [sp + 8] -> x15
  #     const union xnn_f16_minmax_params params[restrict XNN_MIN_ELEMENTS(1)])  [sp + 16] -> (x8)
$else:
  #     const union xnn_f16_minmax_params params[restrict XNN_MIN_ELEMENTS(1)])  [sp + 8] -> (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

# Vector register usage
# A0   v0 v1
# B   v20 v21 v22 v23
# C   v24 v26

# Clamp v4, v5


BEGIN_FUNCTION xnn_f16_gemm${"inc" if INC else ""}_minmax_ukernel_1x8__aarch64_neonfp16arith_ld64

        $if INC:
          # Load cn_stride, acc
          LDP     x14, x15, [sp]
          # Load params pointer
          LDR     x8, [sp, 16]
        $else:
          # Load cn_stride, params pointer
          LDP     x14, x8, [sp]

        # Load params values
        LD2R    {v4.8h, v5.8h}, [x8]
0:
        $if INC:
          # Load initial accumulators
          LDR     q24, [x15], 16
        $else:
          # Load initial bias from w into accumulators
          LDR     q24, [x5], 16

        MOVI    v26.8h, 0               // second set of C for pipelining FMLA

        # Is there at least 4 halffloats (8 bytes)
        SUBS    x0, x2, 8               // k = kc - 8

        B.LO    3f

        # Main loop - 4 halffloats of A (8 bytes)
1:
        LDR     d0, [x3], 8
        LDR     q20, [x5, 0]
        LDR     q21, [x5, 16]
        LDR     q22, [x5, 32]
        LDR     q23, [x5, 48]
        SUBS    x0, x0, 8
        FMLA    v24.8h, v20.8h, v0.h[0]
        FMLA    v26.8h, v21.8h, v0.h[1]
        FMLA    v24.8h, v22.8h, v0.h[2]
        FMLA    v26.8h, v23.8h, v0.h[3]
        ADD     x5, x5, 64
        B.HS    1b

        # Is there a remainder?- 2 halffloats of A (4 bytes)
        TBNZ    x0, 2, 4f
        # Is there a remainder?- 1 halffloat of A (2 bytes)
        TBNZ    x0, 1, 5f

2:
        FADD    v24.8h, v24.8h, v26.8h
        SUBS    x1, x1, 8

        # Clamp
        FMAX    v24.8h, v24.8h, v4.8h
        FMIN    v24.8h, v24.8h, v5.8h

        # Store full 1 x 8
        B.LO    6f

        ST1     {v24.16b},  [x6], x14
        SUB     x3,  x3, x2             // a0 -= kc

        B.HI    0b
        RET

3:
        TBZ     x0, 2, 5f
4:
        # Remainder- 2 halffloats of A (4 bytes)
        LDR     s0, [x3], 4
        LDR     q20, [x5], 16
        LDR     q21, [x5], 16
        FMLA    v24.8h, v20.8h, v0.h[0]
        FMLA    v26.8h, v21.8h, v0.h[1]
        TBZ     x0, 1, 2b

5:
        # Remainder- 1 halffloat of A (2 bytes)
        LDR     h0,  [x3], 2
        LDR     q20, [x5], 16
        FMLA    v24.8h, v20.8h, v0.h[0]
        B       2b

        # Store odd channels
6:
        TBZ     x1, 2, 7f
        STR     d24, [x6], 8
        DUP     d24, v24.d[1]

7:
        TBZ     x1, 1, 8f
        STR     s24, [x6], 4
        DUP     s24, v24.s[1]

8:
        TBZ     x1, 0, 9f
        STR     h24, [x6]
9:
        RET

END_FUNCTION xnn_f16_gemm${"inc" if INC else ""}_minmax_ukernel_1x8__aarch64_neonfp16arith_ld64

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