// 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 # void xnn_f32_dwconv_minmax_ukernel_up4x9__aarch64_neonfma_cortex_a55( # size_t channels, x0, x20 # size_t output_width, x1 # const float** input, x2 # const float* weights, x3, x19 # float* output, x4 # size_t input_stride, x5 # size_t output_increment, x6 # size_t input_offset, x7 # const float* zero, [sp + 64] -> x17 # const xnn_f32_minmax_params params [sp + 72] -> (x16) # d8-d15, x19-x30 need to be preserved if used. x18 is reserved by the OS. # inputs # i0 x8 # i1 x9 # i2 x10 # i3 x11 # i4 x12 # i5 x13 # i6 x14 # i7 x15 # i8 x16 # weights. Bias and 9 weights. # x19 # accumulators # v0-v3 # Input and weight paired values. # Inputs are even and weights are odd registers # v4 v5 # v6 v7 # v10 v11 # v12 v13 # v14 v15 # v16 v17 # v18 v19 # v20 v21 # v22 v23 # v24 v25 # v26 v27 # v28 v29 # Clamp v30 v31 # unused v8 v9 BEGIN_FUNCTION xnn_f32_dwconv_minmax_ukernel_up4x9__aarch64_neonfma_cortex_a55 # Load zero, params pointer LDP x17, x16, [sp] # Save x19-x20,d10-d15 on stack STP x19, x20, [sp, -64]! STP d10, d11, [sp, 16] STP d12, d13, [sp, 32] STP d14, d15, [sp, 48] # Load min/max values LD2R {v30.4s, v31.4s}, [x16] 0: # Load 9 input pointers LDP x8, x9, [x2] LDP x10, x11, [x2, 16] LDP x12, x13, [x2, 32] LDP x14, x15, [x2, 48] LDR x16, [x2, 64] CMP x8, x17 // if i0 == zero ADD x8, x8, x7 // i0 += input_offset CSEL x8, x17, x8, EQ // i0 = zero, else += i0 + input_offset CMP x9, x17 // if i1 == zero ADD x9, x9, x7 // i1 += input_offset CSEL x9, x17, x9, EQ // i1 = zero, else += i1 + input_offset CMP x10, x17 // if i2 == zero ADD x10, x10, x7 // i2 += input_offset CSEL x10, x17, x10, EQ // i2 = zero, else += i2 + input_offset CMP x11, x17 // if i3 == zero ADD x11, x11, x7 // i3 += input_offset CSEL x11, x17, x11, EQ // i3 = zero, else += i3 + input_offset CMP x12, x17 // if i4 == zero ADD x12, x12, x7 // i4 += input_offset CSEL x12, x17, x12, EQ // i4 = zero, else += i4 + input_offset CMP x13, x17 // if i5 == zero ADD x13, x13, x7 // i5 += input_offset CSEL x13, x17, x13, EQ // i5 = zero, else += i5 + input_offset CMP x14, x17 // if i6 == zero ADD x14, x14, x7 // i6 += input_offset CSEL x14, x17, x14, EQ // i6 = zero, else += i6 + input_offset CMP x15, x17 // if i7 == zero ADD x15, x15, x7 // i7 += input_offset CSEL x15, x17, x15, EQ // i7 = zero, else += i7 + input_offset CMP x16, x17 // if i8 == zero ADD x16, x16, x7 // i8 += input_offset CSEL x16, x17, x16, EQ // i8 = zero, else += i8 + input_offset # input += input_stride ADD x2, x2, x5 # x20 := c = channels # c -= 8 SUBS x20, x0, 8 # x19 := w = weights MOV x19, x3 # skip main loop if c < 8 B.LO 3f # SWP prologue # Load vbias.lo LD1 {v0.2S}, [x19], 8 # Load vbias.hi LD1 {v1.2S}, [x19], 8 # Load vi0.lo LD1 {v4.2S}, [x8], 8 # Load vk0.lo LD1 {v5.2S}, [x19], 8 # Load vi0.hi LD1 {v6.2S}, [x8], 8 # Load vk0.hi LD1 {v7.2S}, [x19], 8 # Load vi1.lo LD1 {v28.2S}, [x9], 8 # Load vk1.lo LD1 {v29.2S}, [x19], 8 # Load vi1.hi LD1 {v10.2S}, [x9], 8 # Load vk1.hi LD1 {v11.2S}, [x19], 8 # Load vi2.lo LD1 {v12.2S}, [x10], 8 # Load vk2.lo LD1 {v13.2S}, [x19], 8 # Load vi2.hi LD1 {v14.2S}, [x10], 8 # Load vk2.hi LD1 {v15.2S}, [x19], 8 # Load vi3.lo LD1 {v16.2S}, [x11], 8 # Load vk3.lo LD1 {v17.2S}, [x19], 8 # Load vi3.hi LD1 {v18.2S}, [x11], 8 # Load vk3.hi LD1 {v19.2S}, [x19], 8 # Load vi4.lo LD1 {v20.2S}, [x12], 8 # Load vk4.lo LD1 {v21.2S}, [x19], 8 # Load vi4.hi LD1 {v22.2S}, [x12], 8 # Load vk4.hi LD1 {v23.2S}, [x19], 8 # Load vi5.lo LD1 {v24.2S}, [x13], 8 # Load vk5.lo LD1 {v25.2S}, [x19], 8 # Load vi5.hi LD1 {v26.2S}, [x13], 8 # Load vk5.hi LD1 {v27.2S}, [x19], 8 # vacc.lo += vi0.lo * vk0.lo FMLA v0.2S, v4.2S, v5.2S # Load vi6.lo LD1 {v4.2S}, [x14], 8 # Load vk6.lo LD1 {v5.2S}, [x19], 8 # vacc.hi += vi0.hi * vk0.hi FMLA v1.2S, v6.2S, v7.2S # Load vi6.hi LD1 {v6.2S}, [x14], 8 # Load vk6.hi LD1 {v7.2S}, [x19], 8 # vacc.lo += vi1.lo * vk0.lo FMLA v0.2S, v28.2S, v29.2S # Load vi7.lo LD1 {v28.2S}, [x15], 8 # Load vk7.lo LD1 {v29.2S}, [x19], 8 # vacc.hi += vi1.hi * vk0.hi FMLA v1.2S, v10.2S, v11.2S # Load vi7.hi LD1 {v10.2S}, [x15], 8 # Load vk7.hi LD1 {v11.2S}, [x19], 8 # vacc.lo += vi2.lo * vk2.lo FMLA v0.2S, v12.2S, v13.2S # Load vi8.lo LD1 {v12.2S}, [x16], 8 # Load vk8.lo LD1 {v13.2S}, [x19], 8 # vacc.hi += vi2.hi * vk2.hi FMLA v1.2S, v14.2S, v15.2S # Load vi8.hi LD1 {v14.2S}, [x16], 8 # Load vk8.hi LD1 {v15.2S}, [x19], 8 # Load vbias_next.lo LD1 {v2.2S}, [x19], 8 # Load vbias_next.hi LD1 {v3.2S}, [x19], 8 # vacc.lo += vi3.lo * vk3.lo FMLA v0.2S, v16.2S, v17.2S # Load vi0_next.lo LD1 {v16.2S}, [x8], 8 # Load vk0_next.lo LD1 {v17.2S}, [x19], 8 # vacc.hi += vi3.hi * vk3.hi FMLA v1.2S, v18.2S, v19.2S # Load vi0_next.hi LD1 {v18.2S}, [x8], 8 # Load vk0_next.hi LD1 {v19.2S}, [x19], 8 # vacc.lo += vi4.lo * vk4.lo FMLA v0.2S, v20.2S, v21.2S # Load vi1_next.lo LD1 {v20.2S}, [x9], 8 # Load vk1_next.lo LD1 {v21.2S}, [x19], 8 # vacc.hi += vi4.hi * vk4.hi FMLA v1.2S, v22.2S, v23.2S # Load vi1_next.hi LD1 {v22.2S}, [x9], 8 # Load vk1_next.hi LD1 {v23.2S}, [x19], 8 # vacc.lo += vi5.lo * vk5.lo FMLA v0.2S, v24.2S, v25.2S # Load vi2_next.lo LD1 {v24.2S}, [x10], 8 # Load vk2_next.lo LD1 {v25.2S}, [x19], 8 # vacc.hi += vi5.hi * vk5.hi FMLA v1.2S, v26.2S, v27.2S # Load vi2_next.hi LD1 {v26.2S}, [x10], 8 # Load vk2_next.hi LD1 {v27.2S}, [x19], 8 # vacc.lo += vi6.lo * vk6.lo FMLA v0.2S, v4.2S, v5.2S # Load vi3_next.lo LD1 {v4.2S}, [x11], 8 # Load vk3_next.lo LD1 {v5.2S}, [x19], 8 # vacc.hi += vi6.hi * vk6.hi FMLA v1.2S, v6.2S, v7.2S # Load vi3_next.hi LD1 {v6.2S}, [x11], 8 # Load vk3_next.hi LD1 {v7.2S}, [x19], 8 # vacc.lo += vi7.lo * vk7.lo FMLA v0.2S, v28.2S, v29.2S # Load vi4_next.lo LD1 {v28.2S}, [x12], 8 # Load vk4_next.lo LD1 {v29.2S}, [x19], 8 # vacc.hi += vi7.hi * vk7.hi FMLA v1.2S, v10.2S, v11.2S # Load vi4_next.hi LD1 {v10.2S}, [x12], 8 # Load vk4_next.hi LD1 {v11.2S}, [x19], 8 # vacc.lo += vi8.lo * vk8.lo FMLA v0.2S, v12.2S, v13.2S # Load vi5_next.lo LD1 {v12.2S}, [x13], 8 # Load vk5_next.lo LD1 {v13.2S}, [x19], 8 # vacc.hi += vi8.hi * vk8.hi FMLA v1.2S, v14.2S, v15.2S # Load vi5_next.hi LD1 {v14.2S}, [x13], 8 # Load vk5_next.hi LD1 {v15.2S}, [x19], 8 # vacc_next.lo += vi0_next.lo * vk0_next.lo FMLA v2.2S, v16.2S, v17.2S # Load vi6_next.lo LD1 {v16.2S}, [x14], 8 # vacc.lo = min(vacc.lo, vmin) FMAX v0.2S, v0.2S, v30.2S # Load vk6_next.lo LD1 {v17.2S}, [x19], 8 # vacc_next.hi += vi0_next.hi * vk0_next.hi FMLA v3.2S, v18.2S, v19.2S # Load vi6_next.hi LD1 {v18.2S}, [x14], 8 # vacc.hi = min(vacc.hi, vmin) FMAX v1.2S, v1.2S, v30.2S # Load vk6_next.hi LD1 {v19.2S}, [x19], 8 # vacc_next.lo += vi1_next.lo * vk1_next.lo FMLA v2.2S, v20.2S, v21.2S # Load vi7_next.lo LD1 {v20.2S}, [x15], 8 # vacc.lo = max(vacc.lo, vmax) FMIN v0.2S, v0.2S, v31.2S # Load vk7_next.lo LD1 {v21.2S}, [x19], 8 # vacc_next.hi += vi1_next.hi * vk1_next.hi FMLA v3.2S, v22.2S, v23.2S # Load vi7_next.hi LD1 {v22.2S}, [x15], 8 # vacc.hi = max(vacc.hi, vmax) FMIN v1.2S, v1.2S, v31.2S # Load vk7_next.hi LD1 {v23.2S}, [x19], 8 # vacc_next.lo += vi2_next.lo * vk2_next.lo FMLA v2.2S, v24.2S, v25.2S # Load vi8_next.lo LD1 {v24.2S}, [x16], 8 # Load vk8_next.lo LD1 {v25.2S}, [x19], 8 # vacc_next.hi += vi2_next.hi * vk2_next.hi FMLA v3.2S, v26.2S, v27.2S # Load vi8_next.hi LD1 {v26.2S}, [x16], 8 # Store vacc STP d0, d1, [x4], 16 # c -= 8 SUBS x20, x20, 8 # Load vk8_next.hi LD1 {v27.2S}, [x19], 8 B.LO 2f 1: # SWP iteration # Load vbias.lo LD1 {v0.2S}, [x19], 8 # Load vbias.hi LD1 {v1.2S}, [x19], 8 # vacc_prev.lo += vi3_prev.lo * vk3_prev.lo FMLA v2.2S, v4.2S, v5.2S # Load vi0.lo LD1 {v4.2S}, [x8], 8 # Load vk0.lo LD1 {v5.2S}, [x19], 8 # vacc_prev.hi += vi3_prev.hi * vk3_prev.hi FMLA v3.2S, v6.2S, v7.2S # Load vi0.hi LD1 {v6.2S}, [x8], 8 # Load vk0.hi LD1 {v7.2S}, [x19], 8 # vacc_prev.lo += vi4_prev.lo * vk4_prev.lo FMLA v2.2S, v28.2S, v29.2S # Load vi1.lo LD1 {v28.2S}, [x9], 8 # Load vk1.lo LD1 {v29.2S}, [x19], 8 # vacc_prev.hi += vi4_prev.hi * vk4_prev.hi FMLA v3.2S, v10.2S, v11.2S # Load vi1.hi LD1 {v10.2S}, [x9], 8 # Load vk1.hi LD1 {v11.2S}, [x19], 8 # vacc_prev.lo += vi5_prev.lo * vk5_prev.lo FMLA v2.2S, v12.2S, v13.2S # Load vi2.lo LD1 {v12.2S}, [x10], 8 # Load vk2.lo LD1 {v13.2S}, [x19], 8 # vacc_prev.hi += vi5_prev.hi * vk5_prev.hi FMLA v3.2S, v14.2S, v15.2S # Load vi2.hi LD1 {v14.2S}, [x10], 8 # Load vk2.hi LD1 {v15.2S}, [x19], 8 # vacc_prev.lo += vi6_prev.lo * vk6_prev.lo FMLA v2.2S, v16.2S, v17.2S # Load vi3.lo LD1 {v16.2S}, [x11], 8 # Load vk3.lo LD1 {v17.2S}, [x19], 8 # vacc_prev.hi += vi6_prev.hi * vk6_prev.hi FMLA v3.2S, v18.2S, v19.2S # Load vi3.hi LD1 {v18.2S}, [x11], 8 # Load vk3.hi LD1 {v19.2S}, [x19], 8 # vacc_prev.lo += vi7_prev.lo * vk7_prev.lo FMLA v2.2S, v20.2S, v21.2S # Load vi4.lo LD1 {v20.2S}, [x12], 8 # Load vk4.lo LD1 {v21.2S}, [x19], 8 # vacc_prev.hi += vi7_prev.hi * vk7_prev.hi FMLA v3.2S, v22.2S, v23.2S # Load vi4.hi LD1 {v22.2S}, [x12], 8 # Load vk4.hi LD1 {v23.2S}, [x19], 8 # vacc_prev.lo += vi8_prev.lo * vk8_prev.lo FMLA v2.2S, v24.2S, v25.2S # Load vi5.lo LD1 {v24.2S}, [x13], 8 # Load vk5.lo LD1 {v25.2S}, [x19], 8 # vacc_prev.hi += vi8_prev.hi * vk8_prev.hi FMLA v3.2S, v26.2S, v27.2S # Load vi5.hi LD1 {v26.2S}, [x13], 8 # Load vk5.hi LD1 {v27.2S}, [x19], 8 # vacc.lo += vi0.lo * vk0.lo FMLA v0.2S, v4.2S, v5.2S # Load vi6.lo LD1 {v4.2S}, [x14], 8 # vacc_prev.lo = min(vacc_prev.lo, vmin) FMAX v2.2S, v2.2S, v30.2S # Load vk6.lo LD1 {v5.2S}, [x19], 8 # vacc.hi += vi0.hi * vk0.hi FMLA v1.2S, v6.2S, v7.2S # Load vi6.hi LD1 {v6.2S}, [x14], 8 # vacc_prev.hi = min(vacc_prev.hi, vmin) FMAX v3.2S, v3.2S, v30.2S # Load vk6.hi LD1 {v7.2S}, [x19], 8 # vacc.lo += vi1.lo * vk0.lo FMLA v0.2S, v28.2S, v29.2S # Load vi7.lo LD1 {v28.2S}, [x15], 8 # vacc_prev.lo = max(vacc_prev.lo, vmax) FMIN v2.2S, v2.2S, v31.2S # Load vk7.lo LD1 {v29.2S}, [x19], 8 # vacc.hi += vi1.hi * vk0.hi FMLA v1.2S, v10.2S, v11.2S # Load vi7.hi LD1 {v10.2S}, [x15], 8 # vacc_prev.lo = max(vacc_prev.lo, vmax) FMIN v3.2S, v3.2S, v31.2S # Load vk7.hi LD1 {v11.2S}, [x19], 8 # vacc.lo += vi2.lo * vk2.lo FMLA v0.2S, v12.2S, v13.2S # Load vi8.lo LD1 {v12.2S}, [x16], 8 # Load vk8.lo LD1 {v13.2S}, [x19], 8 # vacc.hi += vi2.hi * vk2.hi FMLA v1.2S, v14.2S, v15.2S # Load vi8.hi LD1 {v14.2S}, [x16], 8 # Store vacc_prev STP d2, d3, [x4], 16 # Load vk8.hi LD1 {v15.2S}, [x19], 8 # Load vbias_next.lo LD1 {v2.2S}, [x19], 8 # Load vbias_next.hi LD1 {v3.2S}, [x19], 8 # vacc.lo += vi3.lo * vk3.lo FMLA v0.2S, v16.2S, v17.2S # Load vi0_next.lo LD1 {v16.2S}, [x8], 8 # Load vk0_next.lo LD1 {v17.2S}, [x19], 8 # vacc.hi += vi3.hi * vk3.hi FMLA v1.2S, v18.2S, v19.2S # Load vi0_next.hi LD1 {v18.2S}, [x8], 8 # Load vk0_next.hi LD1 {v19.2S}, [x19], 8 # vacc.lo += vi4.lo * vk4.lo FMLA v0.2S, v20.2S, v21.2S # Load vi1_next.lo LD1 {v20.2S}, [x9], 8 # Load vk1_next.lo LD1 {v21.2S}, [x19], 8 # vacc.hi += vi4.hi * vk4.hi FMLA v1.2S, v22.2S, v23.2S # Load vi1_next.hi LD1 {v22.2S}, [x9], 8 # Load vk1_next.hi LD1 {v23.2S}, [x19], 8 # vacc.lo += vi5.lo * vk5.lo FMLA v0.2S, v24.2S, v25.2S # Load vi2_next.lo LD1 {v24.2S}, [x10], 8 # Load vk2_next.lo LD1 {v25.2S}, [x19], 8 # vacc.hi += vi5.hi * vk5.hi FMLA v1.2S, v26.2S, v27.2S # Load vi2_next.hi LD1 {v26.2S}, [x10], 8 # Load vk2_next.hi LD1 {v27.2S}, [x19], 8 # vacc.lo += vi6.lo * vk6.lo FMLA v0.2S, v4.2S, v5.2S # Load vi3_next.lo LD1 {v4.2S}, [x11], 8 # Load vk3_next.lo LD1 {v5.2S}, [x19], 8 # vacc.hi += vi6.hi * vk6.hi FMLA v1.2S, v6.2S, v7.2S # Load vi3_next.hi LD1 {v6.2S}, [x11], 8 # Load vk3_next.hi LD1 {v7.2S}, [x19], 8 # vacc.lo += vi7.lo * vk7.lo FMLA v0.2S, v28.2S, v29.2S # Load vi4_next.lo LD1 {v28.2S}, [x12], 8 # Load vk4_next.lo LD1 {v29.2S}, [x19], 8 # vacc.hi += vi7.hi * vk7.hi FMLA v1.2S, v10.2S, v11.2S # Load vi4_next.hi LD1 {v10.2S}, [x12], 8 # Load vk4_next.hi LD1 {v11.2S}, [x19], 8 # vacc.lo += vi8.lo * vk8.lo FMLA v0.2S, v12.2S, v13.2S # Load vi5_next.lo LD1 {v12.2S}, [x13], 8 # Load vk5_next.lo LD1 {v13.2S}, [x19], 8 # vacc.hi += vi8.hi * vk8.hi FMLA v1.2S, v14.2S, v15.2S # Load vi5_next.hi LD1 {v14.2S}, [x13], 8 # Load vk5_next.hi LD1 {v15.2S}, [x19], 8 # vacc_next.lo += vi0_next.lo * vk0_next.lo FMLA v2.2S, v16.2S, v17.2S # Load vi6_next.lo LD1 {v16.2S}, [x14], 8 # vacc.lo = min(vacc.lo, vmin) FMAX v0.2S, v0.2S, v30.2S # Load vk6_next.lo LD1 {v17.2S}, [x19], 8 # vacc_next.hi += vi0_next.hi * vk0_next.hi FMLA v3.2S, v18.2S, v19.2S # Load vi6_next.hi LD1 {v18.2S}, [x14], 8 # vacc.hi = min(vacc.hi, vmin) FMAX v1.2S, v1.2S, v30.2S # Load vk6_next.hi LD1 {v19.2S}, [x19], 8 # vacc_next.lo += vi1_next.lo * vk1_next.lo FMLA v2.2S, v20.2S, v21.2S # Load vi7_next.lo LD1 {v20.2S}, [x15], 8 # vacc.lo = max(vacc.lo, vmax) FMIN v0.2S, v0.2S, v31.2S # Load vk7_next.lo LD1 {v21.2S}, [x19], 8 # vacc_next.hi += vi1_next.hi * vk1_next.hi FMLA v3.2S, v22.2S, v23.2S # Load vi7_next.hi LD1 {v22.2S}, [x15], 8 # vacc.hi = max(vacc.hi, vmax) FMIN v1.2S, v1.2S, v31.2S # Load vk7_next.hi LD1 {v23.2S}, [x19], 8 # vacc_next.lo += vi2_next.lo * vk2_next.lo FMLA v2.2S, v24.2S, v25.2S # Load vi8_next.lo LD1 {v24.2S}, [x16], 8 # Load vk8_next.lo LD1 {v25.2S}, [x19], 8 # vacc_next.hi += vi2_next.hi * vk2_next.hi FMLA v3.2S, v26.2S, v27.2S # Load vi8_next.hi LD1 {v26.2S}, [x16], 8 # Store vacc STP d0, d1, [x4], 16 # c -= 8 SUBS x20, x20, 8 # Load vk8_next.hi LD1 {v27.2S}, [x19], 8 B.HS 1b 2: # SWP epilogue # vacc_prev.lo += vi3_prev.lo * vk3_prev.lo FMLA v2.2S, v4.2S, v5.2S # vacc_prev.hi += vi3_prev.hi * vk3_prev.hi FMLA v3.2S, v6.2S, v7.2S # vacc_prev.lo += vi4_prev.lo * vk4_prev.lo FMLA v2.2S, v28.2S, v29.2S # vacc_prev.hi += vi4_prev.hi * vk4_prev.hi FMLA v3.2S, v10.2S, v11.2S # vacc_prev.lo += vi5_prev.lo * vk5_prev.lo FMLA v2.2S, v12.2S, v13.2S # vacc_prev.hi += vi5_prev.hi * vk5_prev.hi FMLA v3.2S, v14.2S, v15.2S # vacc_prev.lo += vi6_prev.lo * vk6_prev.lo FMLA v2.2S, v16.2S, v17.2S # vacc_prev.hi += vi6_prev.hi * vk6_prev.hi FMLA v3.2S, v18.2S, v19.2S # vacc_prev.lo += vi7_prev.lo * vk7_prev.lo FMLA v2.2S, v20.2S, v21.2S # vacc_prev.hi += vi7_prev.hi * vk7_prev.hi FMLA v3.2S, v22.2S, v23.2S # vacc_prev.lo += vi8_prev.lo * vk8_prev.lo FMLA v2.2S, v24.2S, v25.2S # vacc_prev.hi += vi8_prev.hi * vk8_prev.hi FMLA v3.2S, v26.2S, v27.2S # vacc_prev.lo = min(vacc_prev.lo, vmin) FMAX v2.2S, v2.2S, v30.2S # vacc_prev.hi = min(vacc_prev.hi, vmin) FMAX v3.2S, v3.2S, v30.2S # vacc_prev.lo = max(vacc_prev.lo, vmax) FMIN v2.2S, v2.2S, v31.2S # vacc_prev.lo = max(vacc_prev.lo, vmax) FMIN v3.2S, v3.2S, v31.2S # Store vacc_prev STP d2, d3, [x4], 16 3: # Is there a remainder? - 4 channels TBZ x20, 2, 4f LDR q10, [x8], 16 // load 9 inputs LDP q0, q1, [x19], 32 // load bias and 9 weights LDR q11, [x9], 16 LDR q12, [x10], 16 LDR q13, [x11], 16 LDR q14, [x12], 16 LDR q15, [x13], 16 LDR q16, [x14], 16 LDR q17, [x15], 16 LDR q18, [x16], 16 LDP q2, q3, [x19], 32 LDP q4, q5, [x19], 32 LDP q6, q7, [x19], 32 LDP q28, q29, [x19], 32 FMLA v0.4S, v1.4S, v10.4S FMLA v0.4S, v2.4S, v11.4S FMLA v0.4S, v3.4S, v12.4S FMLA v0.4S, v4.4S, v13.4S FMLA v0.4S, v5.4S, v14.4S FMLA v0.4S, v6.4S, v15.4S FMLA v0.4S, v7.4S, v16.4S FMLA v0.4S, v28.4S, v17.4S FMLA v0.4S, v29.4S, v18.4S FMAX v0.4S, v0.4S, v30.4S FMIN v0.4S, v0.4S, v31.4S STR q0, [x4], 16 4: # Is there a remainder?- 1 to 3 channels TST x20, 3 B.EQ 6f LDR q10, [x8], 16 // load 9 inputs LDP q0, q1, [x19], 32 // load bias and 9 weights LDR q11, [x9], 16 LDR q12, [x10], 16 LDR q13, [x11], 16 LDR q14, [x12], 16 LDR q15, [x13], 16 LDR q16, [x14], 16 LDR q17, [x15], 16 LDR q18, [x16], 16 LDP q2, q3, [x19], 32 LDP q4, q5, [x19], 32 LDP q6, q7, [x19], 32 LDP q28, q29, [x19], 32 FMLA v0.4S, v1.4S, v10.4S FMLA v0.4S, v2.4S, v11.4S FMLA v0.4S, v3.4S, v12.4S FMLA v0.4S, v4.4S, v13.4S FMLA v0.4S, v5.4S, v14.4S FMLA v0.4S, v6.4S, v15.4S FMLA v0.4S, v7.4S, v16.4S FMLA v0.4S, v28.4S, v17.4S FMLA v0.4S, v29.4S, v18.4S FMAX v0.4S, v0.4S, v30.4S FMIN v0.4S, v0.4S, v31.4S TBZ x20, 1, 5f STR d0, [x4], 8 DUP d0, v0.D[1] TBZ x20, 0, 6f 5: STR s0, [x4], 4 6: # output_width -= 1 SUBS x1, x1, 1 # output += output_increment ADD x4, x4, x6 # process next pixel if output_width != 0 B.NE 0b # Restore x19-x20,d10-d15 from stack LDP d14, d15, [sp, 48] LDP d12, d13, [sp, 32] LDP d10, d11, [sp, 16] LDP x19, x20, [sp], 64 RET END_FUNCTION xnn_f32_dwconv_minmax_ukernel_up4x9__aarch64_neonfma_cortex_a55 #ifdef __ELF__ .section ".note.GNU-stack","",%progbits #endif