kernel.bin: file format elf64-littleaarch64 Disassembly of section .text: 0000000000000000 <_binary___libxsmm_abi1_appl_m1_f32_nn_16x4x4_16_4_16_a1_b1_p0_br0_sa0_sb0_uh0_si0_tc_abid_avnni0_bvnni0_cvnni0_mxm_start>: 0: d10303ff sub sp, sp, #0xc0 4: 6d0b27e8 stp d8, d9, [sp, #0xb0] 8: 6d0a2fea stp d10, d11, [sp, #0xa0] c: 6d0937ec stp d12, d13, [sp, #0x90] 10: 6d083fee stp d14, d15, [sp, #0x80] 14: a9026ffa stp x26, x27, [sp, #0x20] 18: a90177fc stp x28, x29, [sp, #0x10] 1c: f90003fe str x30, [sp] 20: 8a00000a and x10, x0, x0 24: f9401140 ldr x0, [x10, #0x20] 28: f9402141 ldr x1, [x10, #0x40] 2c: f9403142 ldr x2, [x10, #0x60] 30: 910003fd mov x29, sp 34: d102a3ff sub sp, sp, #0xa8 38: d29ff80a mov x10, #0xffc0 // =65472 3c: f2bfffea movk x10, #0xffff, lsl #16 40: f2dfffea movk x10, #0xffff, lsl #32 44: f2ffffea movk x10, #0xffff, lsl #48 48: 910003e9 mov x9, sp 4c: 8a0a0129 and x9, x9, x10 50: 9100013f mov sp, x9 54: d2800087 mov x7, #0x4 // =4 58: d2800206 mov x6, #0x10 // =16 5c: 3cc10450 ldr q16, [x2], #0x10 60: 3cc10451 ldr q17, [x2], #0x10 64: 3cc10452 ldr q18, [x2], #0x10 68: 3cc10453 ldr q19, [x2], #0x10 6c: 3cc10454 ldr q20, [x2], #0x10 70: 3cc10455 ldr q21, [x2], #0x10 74: 3cc10456 ldr q22, [x2], #0x10 78: 3cc10457 ldr q23, [x2], #0x10 7c: 3cc10458 ldr q24, [x2], #0x10 80: 3cc10459 ldr q25, [x2], #0x10 84: 3cc1045a ldr q26, [x2], #0x10 88: 3cc1045b ldr q27, [x2], #0x10 8c: 3cc1045c ldr q28, [x2], #0x10 90: 3cc1045d ldr q29, [x2], #0x10 94: 3cc1045e ldr q30, [x2], #0x10 98: 3cc1045f ldr q31, [x2], #0x10 9c: d1040042 sub x2, x2, #0x100 a0: d280008a mov x10, #0x4 // =4 a4: d2800009 mov x9, #0x0 // =0 a8: d280020b mov x11, #0x10 // =16 ac: d280040c mov x12, #0x20 // =32 b0: d280060d mov x13, #0x30 // =48 b4: 3cc10401 ldr q1, [x0], #0x10 b8: 3cc10402 ldr q2, [x0], #0x10 bc: 3cc10403 ldr q3, [x0], #0x10 c0: 3cc10404 ldr q4, [x0], #0x10 c4: bc7f6820 ldr s0, [x1, xzr] c8: 4f801030 fmla v16.4s, v1.4s, v0.s[0] cc: 4f801051 fmla v17.4s, v2.4s, v0.s[0] d0: 4f801072 fmla v18.4s, v3.4s, v0.s[0] d4: 4f801093 fmla v19.4s, v4.4s, v0.s[0] d8: bc6b6820 ldr s0, [x1, x11] dc: 4f801034 fmla v20.4s, v1.4s, v0.s[0] e0: 4f801055 fmla v21.4s, v2.4s, v0.s[0] e4: 4f801076 fmla v22.4s, v3.4s, v0.s[0] e8: 4f801097 fmla v23.4s, v4.4s, v0.s[0] ec: bc6c6820 ldr s0, [x1, x12] f0: 4f801038 fmla v24.4s, v1.4s, v0.s[0] f4: 4f801059 fmla v25.4s, v2.4s, v0.s[0] f8: 4f80107a fmla v26.4s, v3.4s, v0.s[0] fc: 4f80109b fmla v27.4s, v4.4s, v0.s[0] 100: bc6d6820 ldr s0, [x1, x13] 104: 8b0a0021 add x1, x1, x10 108: 8b090000 add x0, x0, x9 10c: 4f80103c fmla v28.4s, v1.4s, v0.s[0] 110: 4f80105d fmla v29.4s, v2.4s, v0.s[0] 114: 4f80107e fmla v30.4s, v3.4s, v0.s[0] 118: 4f80109f fmla v31.4s, v4.4s, v0.s[0] 11c: 3cc10401 ldr q1, [x0], #0x10 120: 3cc10402 ldr q2, [x0], #0x10 124: 3cc10403 ldr q3, [x0], #0x10 128: 3cc10404 ldr q4, [x0], #0x10 12c: bc7f6820 ldr s0, [x1, xzr] 130: 4f801030 fmla v16.4s, v1.4s, v0.s[0] 134: 4f801051 fmla v17.4s, v2.4s, v0.s[0] 138: 4f801072 fmla v18.4s, v3.4s, v0.s[0] 13c: 4f801093 fmla v19.4s, v4.4s, v0.s[0] 140: bc6b6820 ldr s0, [x1, x11] 144: 4f801034 fmla v20.4s, v1.4s, v0.s[0] 148: 4f801055 fmla v21.4s, v2.4s, v0.s[0] 14c: 4f801076 fmla v22.4s, v3.4s, v0.s[0] 150: 4f801097 fmla v23.4s, v4.4s, v0.s[0] 154: bc6c6820 ldr s0, [x1, x12] 158: 4f801038 fmla v24.4s, v1.4s, v0.s[0] 15c: 4f801059 fmla v25.4s, v2.4s, v0.s[0] 160: 4f80107a fmla v26.4s, v3.4s, v0.s[0] 164: 4f80109b fmla v27.4s, v4.4s, v0.s[0] 168: bc6d6820 ldr s0, [x1, x13] 16c: 8b0a0021 add x1, x1, x10 170: 8b090000 add x0, x0, x9 174: 4f80103c fmla v28.4s, v1.4s, v0.s[0] 178: 4f80105d fmla v29.4s, v2.4s, v0.s[0] 17c: 4f80107e fmla v30.4s, v3.4s, v0.s[0] 180: 4f80109f fmla v31.4s, v4.4s, v0.s[0] 184: 3cc10401 ldr q1, [x0], #0x10 188: 3cc10402 ldr q2, [x0], #0x10 18c: 3cc10403 ldr q3, [x0], #0x10 190: 3cc10404 ldr q4, [x0], #0x10 194: bc7f6820 ldr s0, [x1, xzr] 198: 4f801030 fmla v16.4s, v1.4s, v0.s[0] 19c: 4f801051 fmla v17.4s, v2.4s, v0.s[0] 1a0: 4f801072 fmla v18.4s, v3.4s, v0.s[0] 1a4: 4f801093 fmla v19.4s, v4.4s, v0.s[0] 1a8: bc6b6820 ldr s0, [x1, x11] 1ac: 4f801034 fmla v20.4s, v1.4s, v0.s[0] 1b0: 4f801055 fmla v21.4s, v2.4s, v0.s[0] 1b4: 4f801076 fmla v22.4s, v3.4s, v0.s[0] 1b8: 4f801097 fmla v23.4s, v4.4s, v0.s[0] 1bc: bc6c6820 ldr s0, [x1, x12] 1c0: 4f801038 fmla v24.4s, v1.4s, v0.s[0] 1c4: 4f801059 fmla v25.4s, v2.4s, v0.s[0] 1c8: 4f80107a fmla v26.4s, v3.4s, v0.s[0] 1cc: 4f80109b fmla v27.4s, v4.4s, v0.s[0] 1d0: bc6d6820 ldr s0, [x1, x13] 1d4: 8b0a0021 add x1, x1, x10 1d8: 8b090000 add x0, x0, x9 1dc: 4f80103c fmla v28.4s, v1.4s, v0.s[0] 1e0: 4f80105d fmla v29.4s, v2.4s, v0.s[0] 1e4: 4f80107e fmla v30.4s, v3.4s, v0.s[0] 1e8: 4f80109f fmla v31.4s, v4.4s, v0.s[0] 1ec: 3cc10401 ldr q1, [x0], #0x10 1f0: 3cc10402 ldr q2, [x0], #0x10 1f4: 3cc10403 ldr q3, [x0], #0x10 1f8: 3cc10404 ldr q4, [x0], #0x10 1fc: bc7f6820 ldr s0, [x1, xzr] 200: 4f801030 fmla v16.4s, v1.4s, v0.s[0] 204: 4f801051 fmla v17.4s, v2.4s, v0.s[0] 208: 4f801072 fmla v18.4s, v3.4s, v0.s[0] 20c: 4f801093 fmla v19.4s, v4.4s, v0.s[0] 210: bc6b6820 ldr s0, [x1, x11] 214: 4f801034 fmla v20.4s, v1.4s, v0.s[0] 218: 4f801055 fmla v21.4s, v2.4s, v0.s[0] 21c: 4f801076 fmla v22.4s, v3.4s, v0.s[0] 220: 4f801097 fmla v23.4s, v4.4s, v0.s[0] 224: bc6c6820 ldr s0, [x1, x12] 228: 4f801038 fmla v24.4s, v1.4s, v0.s[0] 22c: 4f801059 fmla v25.4s, v2.4s, v0.s[0] 230: 4f80107a fmla v26.4s, v3.4s, v0.s[0] 234: 4f80109b fmla v27.4s, v4.4s, v0.s[0] 238: bc6d6820 ldr s0, [x1, x13] 23c: 8b0a0021 add x1, x1, x10 240: 8b090000 add x0, x0, x9 244: 4f80103c fmla v28.4s, v1.4s, v0.s[0] 248: 4f80105d fmla v29.4s, v2.4s, v0.s[0] 24c: 4f80107e fmla v30.4s, v3.4s, v0.s[0] 250: 4f80109f fmla v31.4s, v4.4s, v0.s[0] 254: d1040000 sub x0, x0, #0x100 258: d1004021 sub x1, x1, #0x10 25c: 3c810450 str q16, [x2], #0x10 260: 3c810451 str q17, [x2], #0x10 264: 3c810452 str q18, [x2], #0x10 268: 3c810453 str q19, [x2], #0x10 26c: 3c810454 str q20, [x2], #0x10 270: 3c810455 str q21, [x2], #0x10 274: 3c810456 str q22, [x2], #0x10 278: 3c810457 str q23, [x2], #0x10 27c: 3c810458 str q24, [x2], #0x10 280: 3c810459 str q25, [x2], #0x10 284: 3c81045a str q26, [x2], #0x10 288: 3c81045b str q27, [x2], #0x10 28c: 3c81045c str q28, [x2], #0x10 290: 3c81045d str q29, [x2], #0x10 294: 3c81045e str q30, [x2], #0x10 298: 3c81045f str q31, [x2], #0x10 29c: d1040042 sub x2, x2, #0x100 2a0: 91010042 add x2, x2, #0x40 2a4: 91010000 add x0, x0, #0x40 2a8: d10040c6 sub x6, x6, #0x10 2ac: b5ffed86 cbnz x6, 0x5c <_binary___libxsmm_abi1_appl_m1_f32_nn_16x4x4_16_4_16_a1_b1_p0_br0_sa0_sb0_uh0_si0_tc_abid_avnni0_bvnni0_cvnni0_mxm_start+0x5c> 2b0: 91030042 add x2, x2, #0xc0 2b4: d1010000 sub x0, x0, #0x40 2b8: 91010021 add x1, x1, #0x40 2bc: d10010e7 sub x7, x7, #0x4 2c0: b5ffecc7 cbnz x7, 0x58 <_binary___libxsmm_abi1_appl_m1_f32_nn_16x4x4_16_4_16_a1_b1_p0_br0_sa0_sb0_uh0_si0_tc_abid_avnni0_bvnni0_cvnni0_mxm_start+0x58> 2c4: 910003bf mov sp, x29 2c8: 6d4b27e8 ldp d8, d9, [sp, #0xb0] 2cc: 6d4a2fea ldp d10, d11, [sp, #0xa0] 2d0: 6d4937ec ldp d12, d13, [sp, #0x90] 2d4: 6d483fee ldp d14, d15, [sp, #0x80] 2d8: a9426ffa ldp x26, x27, [sp, #0x20] 2dc: a94177fc ldp x28, x29, [sp, #0x10] 2e0: f94003fe ldr x30, [sp] 2e4: 910303ff add sp, sp, #0xc0 2e8: d65f03c0 ret