// Auto-generated file. Do not edit! // Template: src/qs8-igemm/4x16-aarch64-neon-mlal-lane-ld64.S.in // Generator: tools/xngen // // Copyright 2021 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_qu8_igemm_minmax_rndnu_ukernel_4x16__aarch64_neon_mlal_lane_prfm_ld64( # size_t mr, x0 # size_t nc, x1 # size_t kc, x2 / x0 # size_t ks, x3 / x9 # const uint8_t** restrict a, x4 # const uint8_t* restrict w, x5 # uint8_t* restrict c, x6 # size_t cm_stride, x7 # size_t cn_stride, [sp] -> x10 # size_t a_offset, [sp + 8] -> x8 # const uint8_t* zero, [sp + 16] -> x12 # const xnn_qs8_conv_minmax_params params [sp + 24] -> (x11) # params structure is 20 bytes # struct { # uint8_t kernel_zero_point[4]; # int32_t right_pre_shift; # int32_t multiplier; # int32_t right_post_shift; # int16_t output_zero_point; # uint8_t output_min; # uint8_t output_max; # } rndnu_neon; # # d8-d15, x19-x30 need to be preserved if used. x18 is reserved by the OS. # Register usage # A0 x13 v0 # A1 x14 v1 # A2 x15 v2 # A3 x20 v3 # B x5 v4 v5 # C0 x6 v16 v20 v24 v28 # C1 x16 v17 v21 v25 v29 # C2 x17 v18 v22 v26 v30 # C3 x7 v19 v23 v27 v31 # zero_point v7 # unused v8 v9 v10 v11 v12 v13 v14 v15 BEGIN_FUNCTION xnn_qu8_igemm_minmax_rndnu_ukernel_4x16__aarch64_neon_mlal_lane_prfm_ld64 # Clamp C pointers CMP x0, 2 // if mr < 2 LDP x10, x8, [sp] // Load cn_stride, a_offset ADD x16, x6, x7 // c1 = c0 + cm_stride CSEL x16, x6, x16, LO // c1 = c0 ADD x17, x16, x7 // c2 = c1 + cm_stride LDP x12, x11, [sp, 16] // Load zero, params pointer // if mr <= 2 CSEL x17, x16, x17, LS // c2 = c1 CMP x0, 4 // if mr < 4 STR x20, [sp, -16]! // Save x20 on stack ADD x7, x17, x7 // c3 = c2 + cm_stride CSEL x7, x17, x7, LO // c3 = c2 LD1R {v7.4s}, [x11] // kernel_zero_point .p2align 3 0: # Load initial bias from w into accumulators LDP q16, q20, [x5], 32 MOV v17.16b, v16.16b MOV v18.16b, v16.16b LDP q24, q28, [x5], 32 MOV v19.16b, v16.16b MOV v21.16b, v20.16b ADD x11, x11, 4 // adjust params pointer MOV v22.16b, v20.16b MOV v23.16b, v20.16b MOV v25.16b, v24.16b MOV v26.16b, v24.16b MOV v27.16b, v24.16b MOV v29.16b, v28.16b MOV v30.16b, v28.16b MOV v31.16b, v28.16b MOV x9, x3 // p = ks .p2align 3 1: # Load next 4 A pointers LDP x13, x14, [x4], 16 LDP x15, x20, [x4], 16 CMP x13, x12 // if a0 == zero ADD x13, x13, x8 // a0 += a_offset CSEL x13, x12, x13, EQ // a0 = zero, else += a0 + a_offset CMP x14, x12 // if a1 == zero ADD x14, x14, x8 // a1 += a_offset CSEL x14, x12, x14, EQ // a1 = zero, else += a1 + a_offset CMP x15, x12 // if a2 == zero ADD x15, x15, x8 // a2 += a_offset CSEL x15, x12, x15, EQ // a2 = zero, else += a2 + a_offset CMP x20, x12 // if a3 == zero ADD x20, x20, x8 // a3 += a_offset CSEL x20, x12, x20, EQ // a3 = zero, else += a3 + a_offset # Is there at least 8 bytes for main loop? SUBS x0, x2, 8 // k = kc - 8 B.LO 4f # Main loop - 8 bytes of A .p2align 3 2: LD1 {v0.8b}, [x13], 8 LDP d4, d5, [x5], 16 LD1 {v1.8b}, [x14], 8 LD1 {v2.8b}, [x15], 8 LD1 {v3.8b}, [x20], 8 UXTL v0.8h, v0.8b USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b UXTL v1.8h, v1.8b UXTL v2.8h, v2.8b UXTL v3.8h, v3.8b SMLAL v16.4s, v4.4h, v0.h[0] SMLAL2 v20.4s, v4.8h, v0.h[0] PRFM PLDL1KEEP, [x13, 128] SMLAL v24.4s, v5.4h, v0.h[0] SMLAL2 v28.4s, v5.8h, v0.h[0] PRFM PLDL1KEEP, [x14, 128] SMLAL v17.4s, v4.4h, v1.h[0] SMLAL2 v21.4s, v4.8h, v1.h[0] PRFM PLDL1KEEP, [x15, 128] SMLAL v25.4s, v5.4h, v1.h[0] SMLAL2 v29.4s, v5.8h, v1.h[0] PRFM PLDL1KEEP, [x20, 128] SMLAL v18.4s, v4.4h, v2.h[0] SMLAL2 v22.4s, v4.8h, v2.h[0] PRFM PLDL1KEEP, [x5, 448] SMLAL v26.4s, v5.4h, v2.h[0] SMLAL2 v30.4s, v5.8h, v2.h[0] PRFM PLDL1KEEP, [x5, 512] SMLAL v19.4s, v4.4h, v3.h[0] SMLAL2 v23.4s, v4.8h, v3.h[0] SMLAL v27.4s, v5.4h, v3.h[0] SMLAL2 v31.4s, v5.8h, v3.h[0] LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[1] SMLAL2 v20.4s, v4.8h, v0.h[1] SMLAL v24.4s, v5.4h, v0.h[1] SMLAL2 v28.4s, v5.8h, v0.h[1] SMLAL v17.4s, v4.4h, v1.h[1] SMLAL2 v21.4s, v4.8h, v1.h[1] SMLAL v25.4s, v5.4h, v1.h[1] SMLAL2 v29.4s, v5.8h, v1.h[1] SMLAL v18.4s, v4.4h, v2.h[1] SMLAL2 v22.4s, v4.8h, v2.h[1] SMLAL v26.4s, v5.4h, v2.h[1] SMLAL2 v30.4s, v5.8h, v2.h[1] SMLAL v19.4s, v4.4h, v3.h[1] SMLAL2 v23.4s, v4.8h, v3.h[1] SMLAL v27.4s, v5.4h, v3.h[1] SMLAL2 v31.4s, v5.8h, v3.h[1] LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[2] SMLAL2 v20.4s, v4.8h, v0.h[2] SMLAL v24.4s, v5.4h, v0.h[2] SMLAL2 v28.4s, v5.8h, v0.h[2] SMLAL v17.4s, v4.4h, v1.h[2] SMLAL2 v21.4s, v4.8h, v1.h[2] SMLAL v25.4s, v5.4h, v1.h[2] SMLAL2 v29.4s, v5.8h, v1.h[2] SMLAL v18.4s, v4.4h, v2.h[2] SMLAL2 v22.4s, v4.8h, v2.h[2] SMLAL v26.4s, v5.4h, v2.h[2] SMLAL2 v30.4s, v5.8h, v2.h[2] SMLAL v19.4s, v4.4h, v3.h[2] SMLAL2 v23.4s, v4.8h, v3.h[2] SMLAL v27.4s, v5.4h, v3.h[2] SMLAL2 v31.4s, v5.8h, v3.h[2] LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[3] SMLAL2 v20.4s, v4.8h, v0.h[3] SMLAL v24.4s, v5.4h, v0.h[3] SMLAL2 v28.4s, v5.8h, v0.h[3] SMLAL v17.4s, v4.4h, v1.h[3] SMLAL2 v21.4s, v4.8h, v1.h[3] SMLAL v25.4s, v5.4h, v1.h[3] SMLAL2 v29.4s, v5.8h, v1.h[3] SMLAL v18.4s, v4.4h, v2.h[3] SMLAL2 v22.4s, v4.8h, v2.h[3] SMLAL v26.4s, v5.4h, v2.h[3] SMLAL2 v30.4s, v5.8h, v2.h[3] SMLAL v19.4s, v4.4h, v3.h[3] SMLAL2 v23.4s, v4.8h, v3.h[3] SMLAL v27.4s, v5.4h, v3.h[3] SMLAL2 v31.4s, v5.8h, v3.h[3] LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[4] SMLAL2 v20.4s, v4.8h, v0.h[4] SMLAL v24.4s, v5.4h, v0.h[4] SMLAL2 v28.4s, v5.8h, v0.h[4] SMLAL v17.4s, v4.4h, v1.h[4] SMLAL2 v21.4s, v4.8h, v1.h[4] SMLAL v25.4s, v5.4h, v1.h[4] SMLAL2 v29.4s, v5.8h, v1.h[4] SMLAL v18.4s, v4.4h, v2.h[4] SMLAL2 v22.4s, v4.8h, v2.h[4] SMLAL v26.4s, v5.4h, v2.h[4] SMLAL2 v30.4s, v5.8h, v2.h[4] SMLAL v19.4s, v4.4h, v3.h[4] SMLAL2 v23.4s, v4.8h, v3.h[4] SMLAL v27.4s, v5.4h, v3.h[4] SMLAL2 v31.4s, v5.8h, v3.h[4] LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[5] SMLAL2 v20.4s, v4.8h, v0.h[5] SMLAL v24.4s, v5.4h, v0.h[5] SMLAL2 v28.4s, v5.8h, v0.h[5] SMLAL v17.4s, v4.4h, v1.h[5] SMLAL2 v21.4s, v4.8h, v1.h[5] SMLAL v25.4s, v5.4h, v1.h[5] SMLAL2 v29.4s, v5.8h, v1.h[5] SMLAL v18.4s, v4.4h, v2.h[5] SMLAL2 v22.4s, v4.8h, v2.h[5] SMLAL v26.4s, v5.4h, v2.h[5] SMLAL2 v30.4s, v5.8h, v2.h[5] SMLAL v19.4s, v4.4h, v3.h[5] SMLAL2 v23.4s, v4.8h, v3.h[5] SMLAL v27.4s, v5.4h, v3.h[5] SMLAL2 v31.4s, v5.8h, v3.h[5] LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[6] SMLAL2 v20.4s, v4.8h, v0.h[6] SMLAL v24.4s, v5.4h, v0.h[6] SMLAL2 v28.4s, v5.8h, v0.h[6] SMLAL v17.4s, v4.4h, v1.h[6] SMLAL2 v21.4s, v4.8h, v1.h[6] SMLAL v25.4s, v5.4h, v1.h[6] SMLAL2 v29.4s, v5.8h, v1.h[6] SMLAL v18.4s, v4.4h, v2.h[6] SMLAL2 v22.4s, v4.8h, v2.h[6] SMLAL v26.4s, v5.4h, v2.h[6] SMLAL2 v30.4s, v5.8h, v2.h[6] SMLAL v19.4s, v4.4h, v3.h[6] SMLAL2 v23.4s, v4.8h, v3.h[6] SMLAL v27.4s, v5.4h, v3.h[6] SMLAL2 v31.4s, v5.8h, v3.h[6] LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[7] SMLAL2 v20.4s, v4.8h, v0.h[7] SMLAL v24.4s, v5.4h, v0.h[7] SMLAL2 v28.4s, v5.8h, v0.h[7] SMLAL v17.4s, v4.4h, v1.h[7] SMLAL2 v21.4s, v4.8h, v1.h[7] SMLAL v25.4s, v5.4h, v1.h[7] SMLAL2 v29.4s, v5.8h, v1.h[7] SMLAL v18.4s, v4.4h, v2.h[7] SMLAL2 v22.4s, v4.8h, v2.h[7] SMLAL v26.4s, v5.4h, v2.h[7] SMLAL2 v30.4s, v5.8h, v2.h[7] SMLAL v19.4s, v4.4h, v3.h[7] SMLAL2 v23.4s, v4.8h, v3.h[7] SMLAL v27.4s, v5.4h, v3.h[7] SMLAL2 v31.4s, v5.8h, v3.h[7] SUBS x0, x0, 8 B.HS 2b AND x0, x2, 7 // kc remainder 0 to 7 # Is there a remainder?- 1 to 7 bytes of A CBNZ x0, 4f 3: # ks loop SUBS x9, x9, 32 // ks -= MR * sizeof(uint8_t*) B.HI 1b # Apply params - preshift, scale, postshift, bias and clamp LD1R {v4.4s}, [x11], 4 SQSHL v16.4s, v16.4s, v4.4s // shift to upper bits SQSHL v17.4s, v17.4s, v4.4s SQSHL v18.4s, v18.4s, v4.4s SQSHL v19.4s, v19.4s, v4.4s SQSHL v20.4s, v20.4s, v4.4s SQSHL v21.4s, v21.4s, v4.4s SQSHL v22.4s, v22.4s, v4.4s SQSHL v23.4s, v23.4s, v4.4s LD1R {v5.4s}, [x11], 4 SQSHL v24.4s, v24.4s, v4.4s SQSHL v25.4s, v25.4s, v4.4s SQSHL v26.4s, v26.4s, v4.4s SQSHL v27.4s, v27.4s, v4.4s SQSHL v28.4s, v28.4s, v4.4s SQSHL v29.4s, v29.4s, v4.4s SQSHL v30.4s, v30.4s, v4.4s SQSHL v31.4s, v31.4s, v4.4s LD1R {v6.4s}, [x11], 4 SQDMULH v16.4s, v16.4s, v5.4s // scale without rounding SQDMULH v17.4s, v17.4s, v5.4s SQDMULH v18.4s, v18.4s, v5.4s SQDMULH v19.4s, v19.4s, v5.4s SQDMULH v20.4s, v20.4s, v5.4s SQDMULH v21.4s, v21.4s, v5.4s SQDMULH v22.4s, v22.4s, v5.4s SQDMULH v23.4s, v23.4s, v5.4s SQDMULH v24.4s, v24.4s, v5.4s SQDMULH v25.4s, v25.4s, v5.4s SQDMULH v26.4s, v26.4s, v5.4s SQDMULH v27.4s, v27.4s, v5.4s SQDMULH v28.4s, v28.4s, v5.4s SQDMULH v29.4s, v29.4s, v5.4s SQDMULH v30.4s, v30.4s, v5.4s SQDMULH v31.4s, v31.4s, v5.4s SRSHL v16.4s, v16.4s, v6.4s // signed rounding shift left SRSHL v17.4s, v17.4s, v6.4s SRSHL v18.4s, v18.4s, v6.4s SRSHL v19.4s, v19.4s, v6.4s SRSHL v20.4s, v20.4s, v6.4s SRSHL v21.4s, v21.4s, v6.4s SRSHL v22.4s, v22.4s, v6.4s SRSHL v23.4s, v23.4s, v6.4s SRSHL v24.4s, v24.4s, v6.4s SRSHL v25.4s, v25.4s, v6.4s SRSHL v26.4s, v26.4s, v6.4s SRSHL v27.4s, v27.4s, v6.4s SRSHL v28.4s, v28.4s, v6.4s SRSHL v29.4s, v29.4s, v6.4s SRSHL v30.4s, v30.4s, v6.4s SRSHL v31.4s, v31.4s, v6.4s SQXTN v16.4h, v16.4s SQXTN v17.4h, v17.4s SQXTN v18.4h, v18.4s SQXTN v19.4h, v19.4s SQXTN v24.4h, v24.4s SQXTN v25.4h, v25.4s SQXTN v26.4h, v26.4s SQXTN v27.4h, v27.4s LD1R {v6.8h}, [x11], 2 // add bias SQXTN2 v16.8h, v20.4s SQXTN2 v17.8h, v21.4s SQXTN2 v18.8h, v22.4s SQXTN2 v19.8h, v23.4s SQXTN2 v24.8h, v28.4s SQXTN2 v25.8h, v29.4s SQXTN2 v26.8h, v30.4s SQXTN2 v27.8h, v31.4s SQADD v16.8h, v16.8h, v6.8h SQADD v17.8h, v17.8h, v6.8h SQADD v18.8h, v18.8h, v6.8h SQADD v19.8h, v19.8h, v6.8h SQADD v24.8h, v24.8h, v6.8h SQADD v25.8h, v25.8h, v6.8h SQADD v26.8h, v26.8h, v6.8h SQADD v27.8h, v27.8h, v6.8h LD1R {v4.16b}, [x11], 1 // clamp min value SQXTUN v0.8b, v16.8h SQXTUN v1.8b, v17.8h SQXTUN v2.8b, v18.8h SQXTUN v3.8b, v19.8h LD1R {v5.16b}, [x11] // clamp max value SQXTUN2 v0.16b, v24.8h SQXTUN2 v1.16b, v25.8h SQXTUN2 v2.16b, v26.8h SQXTUN2 v3.16b, v27.8h SUB x11, x11, 19 // rewind params pointer UMAX v0.16b, v0.16b, v4.16b UMAX v1.16b, v1.16b, v4.16b UMAX v2.16b, v2.16b, v4.16b UMAX v3.16b, v3.16b, v4.16b SUBS x1, x1, 16 UMIN v0.16b, v0.16b, v5.16b UMIN v1.16b, v1.16b, v5.16b UMIN v2.16b, v2.16b, v5.16b UMIN v3.16b, v3.16b, v5.16b B.LO 5f # Store full 4 x 16 ST1 {v3.16b}, [x7], x10 ST1 {v2.16b}, [x17], x10 ST1 {v1.16b}, [x16], x10 ST1 {v0.16b}, [x6], x10 SUB x4, x4, x3 // a -= ks # nc loop B.HI 0b # Restore x20 from stack LDR x20, [sp], 16 RET # Remainder- 1 to 7 bytes of A .p2align 3 4: AND x0, x2, 7 // kc remainder 1 to 7 LD1 {v0.8b}, [x13], x0 LDP d4, d5, [x5], 16 LD1 {v1.8b}, [x14], x0 LD1 {v2.8b}, [x15], x0 LD1 {v3.8b}, [x20], x0 UXTL v0.8h, v0.8b USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b UXTL v1.8h, v1.8b UXTL v2.8h, v2.8b UXTL v3.8h, v3.8b SMLAL v16.4s, v4.4h, v0.h[0] SMLAL2 v20.4s, v4.8h, v0.h[0] SMLAL v24.4s, v5.4h, v0.h[0] SMLAL2 v28.4s, v5.8h, v0.h[0] SMLAL v17.4s, v4.4h, v1.h[0] SMLAL2 v21.4s, v4.8h, v1.h[0] SMLAL v25.4s, v5.4h, v1.h[0] SMLAL2 v29.4s, v5.8h, v1.h[0] SMLAL v18.4s, v4.4h, v2.h[0] SMLAL2 v22.4s, v4.8h, v2.h[0] SMLAL v26.4s, v5.4h, v2.h[0] SMLAL2 v30.4s, v5.8h, v2.h[0] SMLAL v19.4s, v4.4h, v3.h[0] SMLAL2 v23.4s, v4.8h, v3.h[0] SMLAL v27.4s, v5.4h, v3.h[0] SMLAL2 v31.4s, v5.8h, v3.h[0] CMP x0, 2 B.LO 3b LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[1] SMLAL2 v20.4s, v4.8h, v0.h[1] SMLAL v24.4s, v5.4h, v0.h[1] SMLAL2 v28.4s, v5.8h, v0.h[1] SMLAL v17.4s, v4.4h, v1.h[1] SMLAL2 v21.4s, v4.8h, v1.h[1] SMLAL v25.4s, v5.4h, v1.h[1] SMLAL2 v29.4s, v5.8h, v1.h[1] SMLAL v18.4s, v4.4h, v2.h[1] SMLAL2 v22.4s, v4.8h, v2.h[1] SMLAL v26.4s, v5.4h, v2.h[1] SMLAL2 v30.4s, v5.8h, v2.h[1] SMLAL v19.4s, v4.4h, v3.h[1] SMLAL2 v23.4s, v4.8h, v3.h[1] SMLAL v27.4s, v5.4h, v3.h[1] SMLAL2 v31.4s, v5.8h, v3.h[1] B.EQ 3b LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[2] SMLAL2 v20.4s, v4.8h, v0.h[2] SMLAL v24.4s, v5.4h, v0.h[2] SMLAL2 v28.4s, v5.8h, v0.h[2] SMLAL v17.4s, v4.4h, v1.h[2] SMLAL2 v21.4s, v4.8h, v1.h[2] SMLAL v25.4s, v5.4h, v1.h[2] SMLAL2 v29.4s, v5.8h, v1.h[2] SMLAL v18.4s, v4.4h, v2.h[2] SMLAL2 v22.4s, v4.8h, v2.h[2] SMLAL v26.4s, v5.4h, v2.h[2] SMLAL2 v30.4s, v5.8h, v2.h[2] SMLAL v19.4s, v4.4h, v3.h[2] SMLAL2 v23.4s, v4.8h, v3.h[2] SMLAL v27.4s, v5.4h, v3.h[2] SMLAL2 v31.4s, v5.8h, v3.h[2] CMP x0, 4 B.LO 3b LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[3] SMLAL2 v20.4s, v4.8h, v0.h[3] SMLAL v24.4s, v5.4h, v0.h[3] SMLAL2 v28.4s, v5.8h, v0.h[3] SMLAL v17.4s, v4.4h, v1.h[3] SMLAL2 v21.4s, v4.8h, v1.h[3] SMLAL v25.4s, v5.4h, v1.h[3] SMLAL2 v29.4s, v5.8h, v1.h[3] SMLAL v18.4s, v4.4h, v2.h[3] SMLAL2 v22.4s, v4.8h, v2.h[3] SMLAL v26.4s, v5.4h, v2.h[3] SMLAL2 v30.4s, v5.8h, v2.h[3] SMLAL v19.4s, v4.4h, v3.h[3] SMLAL2 v23.4s, v4.8h, v3.h[3] SMLAL v27.4s, v5.4h, v3.h[3] SMLAL2 v31.4s, v5.8h, v3.h[3] B.EQ 3b LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[4] SMLAL2 v20.4s, v4.8h, v0.h[4] SMLAL v24.4s, v5.4h, v0.h[4] SMLAL2 v28.4s, v5.8h, v0.h[4] SMLAL v17.4s, v4.4h, v1.h[4] SMLAL2 v21.4s, v4.8h, v1.h[4] SMLAL v25.4s, v5.4h, v1.h[4] SMLAL2 v29.4s, v5.8h, v1.h[4] SMLAL v18.4s, v4.4h, v2.h[4] SMLAL2 v22.4s, v4.8h, v2.h[4] SMLAL v26.4s, v5.4h, v2.h[4] SMLAL2 v30.4s, v5.8h, v2.h[4] SMLAL v19.4s, v4.4h, v3.h[4] SMLAL2 v23.4s, v4.8h, v3.h[4] SMLAL v27.4s, v5.4h, v3.h[4] SMLAL2 v31.4s, v5.8h, v3.h[4] CMP x0, 6 B.LO 3b LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[5] SMLAL2 v20.4s, v4.8h, v0.h[5] SMLAL v24.4s, v5.4h, v0.h[5] SMLAL2 v28.4s, v5.8h, v0.h[5] SMLAL v17.4s, v4.4h, v1.h[5] SMLAL2 v21.4s, v4.8h, v1.h[5] SMLAL v25.4s, v5.4h, v1.h[5] SMLAL2 v29.4s, v5.8h, v1.h[5] SMLAL v18.4s, v4.4h, v2.h[5] SMLAL2 v22.4s, v4.8h, v2.h[5] SMLAL v26.4s, v5.4h, v2.h[5] SMLAL2 v30.4s, v5.8h, v2.h[5] SMLAL v19.4s, v4.4h, v3.h[5] SMLAL2 v23.4s, v4.8h, v3.h[5] SMLAL v27.4s, v5.4h, v3.h[5] SMLAL2 v31.4s, v5.8h, v3.h[5] B.EQ 3b LDP d4, d5, [x5], 16 USUBL v4.8h, v4.8b, v7.8b USUBL v5.8h, v5.8b, v7.8b SMLAL v16.4s, v4.4h, v0.h[6] SMLAL2 v20.4s, v4.8h, v0.h[6] SMLAL v24.4s, v5.4h, v0.h[6] SMLAL2 v28.4s, v5.8h, v0.h[6] SMLAL v17.4s, v4.4h, v1.h[6] SMLAL2 v21.4s, v4.8h, v1.h[6] SMLAL v25.4s, v5.4h, v1.h[6] SMLAL2 v29.4s, v5.8h, v1.h[6] SMLAL v18.4s, v4.4h, v2.h[6] SMLAL2 v22.4s, v4.8h, v2.h[6] SMLAL v26.4s, v5.4h, v2.h[6] SMLAL2 v30.4s, v5.8h, v2.h[6] SMLAL v19.4s, v4.4h, v3.h[6] SMLAL2 v23.4s, v4.8h, v3.h[6] SMLAL v27.4s, v5.4h, v3.h[6] SMLAL2 v31.4s, v5.8h, v3.h[6] B 3b # Store odd width .p2align 3 5: TBZ x1, 3, 6f STR d3, [x7], 8 STR d2, [x17], 8 DUP d3, v3.d[1] DUP d2, v2.d[1] STR d1, [x16], 8 STR d0, [x6], 8 DUP d1, v1.d[1] DUP d0, v0.d[1] 6: TBZ x1, 2, 7f STR s3, [x7], 4 STR s2, [x17], 4 DUP s3, v3.s[1] DUP s2, v2.s[1] STR s1, [x16], 4 STR s0, [x6], 4 DUP s1, v1.s[1] DUP s0, v0.s[1] 7: TBZ x1, 1, 8f STR h3, [x7], 2 STR h2, [x17], 2 DUP h3, v3.h[1] DUP h2, v2.h[1] STR h1, [x16], 2 STR h0, [x6], 2 DUP h1, v1.h[1] DUP h0, v0.h[1] 8: TBZ x1, 0, 9f STR b3, [x7] STR b2, [x17] STR b1, [x16] STR b0, [x6] 9: # Restore x20 from stack LDR x20, [sp], 16 RET END_FUNCTION xnn_qu8_igemm_minmax_rndnu_ukernel_4x16__aarch64_neon_mlal_lane_prfm_ld64 #ifdef __ELF__ .section ".note.GNU-stack","",%progbits #endif