Apple M1 Microarchitecture Research by Dougall Johnson

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

ADD (vector, D)

Test 1: uops

Code:

  add d0, d0, d1
  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)03181e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150361168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037160061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100002073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100001373116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  add d0, d0, d1
  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)03191e3f4e51inst 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
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001207101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001003607101161119791100001002003820038200382003820038
102042008615000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010044907101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100012907101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010006607101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000648006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000306402162219785010000102003820038200382003820038
10024200371500000016119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000053619687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  add d0, d1, d0
  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)03191e3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715200611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200862003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110202100991001001000010000071021622197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100053071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002035420037200371110201100991001001000010002071021622197910100001002003820038200382003820038
1020420037150001561968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
1020420037150002231968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03041e1f3f4e51inst 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)9fa0a6a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715010061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001002030640216221978510000102003820038200382003820038
10024200371500207132441196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000001640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182008520073184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000082196872510023101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221982410000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000640216221978510000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  add d0, d8, d9
  add d1, d8, d9
  add d2, d8, d9
  add d3, d8, d9
  add d4, d8, d9
  add d5, d8, d9
  add d6, d8, d9
  add d7, d8, d9
  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)9fa0a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042010815104025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000081051103162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000087051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010001470051102162220035800001002003920039200392003920039
8020420038150154054801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000090051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100029051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004715002238258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001001005024191616172003580000102003920039200392003920039
800242003815602103258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000005024121613292003580000102003920039200392003920039
800242003815002145258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000005024161615242003580000102003920039200392003920039
80024200381500240258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000605024141615262003580000102003920039200392003920039
80024200381500240258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000005024171612152003580000102003920039200392003920039
80024200381505822103258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005024171614252003580000102003920039200392003920039
80024200381500240258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001001005024161614162003580000102003920039200392003920039
80024200381500240258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000005024151613152003580000102003920039200392003920039
800242003815002504258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000005024141617312003580000102003920039200392003920039
8002420038150021029258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000005024161616152003580000102003920039200392003920039