Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

ORN (vector, 16B)

Test 1: uops

Code:

  orn v0.16b, v0.16b, v1.16b
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160103168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715661168725100010001000264680120182037203715723189510001000200020372037111001100001073116111787100020382038203820382038
100420371515244168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150107168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  orn v0.16b, v0.16b, v1.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000307101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000631196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001003210807101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037149000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844403187671001020100002020000200372003711100211091010100001040003100006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219850010000102003820038200382003820038
100242003714900000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000003006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000003006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  orn v0.16b, v1.16b, v0.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03090b1e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968725101611001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
102042003715000001061968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001009207101161119791100001002003820038200382003820038
102042003715000005391968725101001001000010010000552284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500012176611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000641968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
10204200371501100641967625101001001000010010000500284768002001820037200851842403187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000641968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010036402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242008515006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100126402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715004411968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  orn v0.16b, v8.16b, v9.16b
  orn v1.16b, v8.16b, v9.16b
  orn v2.16b, v8.16b, v9.16b
  orn v3.16b, v8.16b, v9.16b
  orn v4.16b, v8.16b, v9.16b
  orn v5.16b, v8.16b, v9.16b
  orn v6.16b, v8.16b, v9.16b
  orn v7.16b, v8.16b, v9.16b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03181e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004914900402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051103161120035800001002003920039200392003920039
8020420038150001682580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001001351101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002008820039200392003920039
802042003815000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100147851101161120035800001002003920039200392003920039
8020420038150001052580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150001662580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000020019200382003899733999680100200800002001600002003820038118020110099100100800001001351101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0308181e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471500003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000010140505020316332003580000102003920039200392003920039
800242003815000019425800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020316322003580000102003920039200392003920088
800242003815010014225800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020316332003580000102003920039200392003920039
80024200381500003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020316232003580000102003920039200392003920039
80024200381500003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001010200005037316242003580000102003920039200392003920039
80024200381500008125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005038226232008380000102003920039200392003920039
80024200381500003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020316332003580000102003920039200392003920039
80024200381500003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020316332003580000102003920039200392003920039
800242003815000035125800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020316332003580000102003920039200392003920039
80024200381500003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020216232003580000102003920039200392003920039