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, 2D)

Test 1: uops

Code:

  add v0.2d, v0.2d, v1.2d
  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)030708090b18191e1f3a3f4e51inst 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)a0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500000000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
100420371500000000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
100420371500000000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
100420371500000000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073316221787100020382038203820382038
100420371500001190061168725100010001000264680020182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
1004203715000000570061168725100010001000264680120182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
100420371600000000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
100420371500000000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
100420371500000000061168725100010001000264680020182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038
100420371500000000061168725100010001000264680120182037203715723189510001000200020372037111001100000000073316331787100020382038203820382038

Test 2: Latency 1->2

Code:

  add v0.2d, v0.2d, v1.2d
  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)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)9fa7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150276119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150021919687251013610010012112100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100010071021622197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150323719687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100120071024222197910100001002003820038200382003820038
102052003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
102042003715106119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371502346119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500006008219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000064919687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500003006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000015006119687251001010100001010000502847680020018200372003718460318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000000053619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  add v0.2d, v1.2d, v0.2d
  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)030b18191e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000056228476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150001061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100114407101161119791100001002003820038200382003820038

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)9fa6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037149061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102008520038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
10024200371501261196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  add v0.2d, v8.2d, v9.2d
  add v1.2d, v8.2d, v9.2d
  add v2.2d, v8.2d, v9.2d
  add v3.2d, v8.2d, v9.2d
  add v4.2d, v8.2d, v9.2d
  add v5.2d, v8.2d, v9.2d
  add v6.2d, v8.2d, v9.2d
  add v7.2d, v8.2d, v9.2d
  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)031e1f3f51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000120511031602200350800001002003920039200392003920039
80204200381500012825803081008000010080000500640000120019200382003899730310103801002008000020016000020038200381180201100991001008000010000000511011611200730800001002003920039200392003920039
802042003815021012825801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100003103511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e3f51inst 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)9fa8acc2cfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150000039258001012800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050200216232003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050200216222003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001006050203416222003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050200416232003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050200116222003580000102003920039200392003920039
800242003815000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000102366050200316232003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001009050200216222003580000102003920039200392003920100
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010503050200316222003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001003050200216222003580000102003920039200392003920039
80024200381500000392580010108000010800005064000012001920038200389996310018800102080000201600002008720038118002110910108000010099050200316222003580000102003920039200392003920039