Apple M1 Microarchitecture Research by Dougall Johnson

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

AND (vector, 8B)

Test 1: uops

Code:

  and v0.8b, v0.8b, v1.8b
  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)03080b1e1f3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000054116762510121000100026468002022208520371574319251000115320002037208421100110000196094116111803100021222086208520382038
1004203715010886116874410001000100026468012018203720371572318951000100020002085203711100110000180379137111787100020382086203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371500006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371600006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  and v0.8b, v0.8b, v1.8b
  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)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)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
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715051611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150468611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150558611968725101001001000010010000500284768020018200372003718422318745101002141000020420000200372003711102011009910010010000100007102162219791100001002003820085200382003820038
10204200371500611968725101001001000012210152633284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003721102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101141001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
1020420037150591611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000540084196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000010306409164419785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006406165619785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001220100002020000200372003711100211091010100001000000006404166519785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006405165519785010000102003820038200382003820038
1002420037150000000061196872510010101001210100005028476800200182003720037184443187671016320100002020650200842003731100211091010100001000000306405165519785010000102017920038200382003820038
1002420085151100000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006405165519785010000102003820038200382003820038
10024200371500000120061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006406166419785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006406166519785010000102003820038200382003820038
10024200371500000120061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000200397306405166519785010000102003820038200382003820038
100242003715000001680061196872510010101000011100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006406166619785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  and v0.8b, v1.8b, v0.8b
  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)03080b1e3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100204100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715001061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820085200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308091e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001020640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001050640216221978510000102003820038200382003820038
100242003714900061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000361196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671016420100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715010061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371500010861196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  and v0.8b, v8.8b, v9.8b
  and v1.8b, v8.8b, v9.8b
  and v2.8b, v8.8b, v9.8b
  and v3.8b, v8.8b, v9.8b
  and v4.8b, v8.8b, v9.8b
  and v5.8b, v8.8b, v9.8b
  and v6.8b, v8.8b, v9.8b
  and v7.8b, v8.8b, v9.8b
  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)031e3f51inst 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)9fa0a1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150812925802041008000810080020500640132120019200382003899776998980120200800322001600642003820038118020110099100100800001000000011151180161020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322001600642003820038118020110099100100800001000000011151180160020035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002010120039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
8020420038150244025801721008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997331007480100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
80204200381502140258019510480000100800005006400001200192003820038997371002180100200800002001600002003820038118020110099100100800001000000000051101161120035800001002003920039200392003920039
802042003815006125801001008000010080000500640000120019200382003899733999680316200800002001600002003820038118020110099100100800001002200000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)6061696d6edispatch 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)9fa8accfd0d2d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000000392580010108000010800005064000010200192003820038999631001880010208000020160000200382003811800211091010800001000502050161601782003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100050205081608172003580000102003920039200392003920039
80024200381500000000039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100050205061606172003580000102003920039200392003920039
800242003815000000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000502050171601792003580000102003920039200392003920039
80024200381500000033900392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001038050205081601762003580000102003920039200392003920039
800242003815000000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000502050171601782003580000102003920039200392003920039
800242003815000000000392580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000504850816017172003580000102003920039200392003920039
80024200381500000000070425800101080000108000050640000152001920038200389996310018800102080000201600002003820038118002110910108000010005020501716017172003580000102003920039200392003920039
800242003815000000000392580010108000010800005064000005200192003820038999631001880010208000020160000200382003811800211091010800001000502050171608172003580000102003920039200392003920039
8002420038150000000003925800101080000108000050640000052001920038200389996310018800102080000201600002003820038118002110910108000010005020001716017172003580000102003920039200392003920039