Apple M1 Microarchitecture Research by Dougall Johnson

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

FMIN (scalar, D)

Test 1: uops

Code:

  fmin 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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037153611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037153611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmin 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)031e3a3f4e5051inst 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)9facc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968702510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010015307101161119791100001002003820038200382003820038
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150906119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100307101161119791100001002003820038200382003820038
1020420037150006119687025101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100120640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100210640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000101150640216221978510000102003820038200382003820038
10024200371500168196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500124196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmin 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)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)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)9fa8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680020018200372003718429071874010100200100082002001620037200371110201100991001001000010000181117180160019802100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842906187401010020010008200200162003720037111020110099100100100001000001117180160019802100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001001000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715002331968725101001001000010010000500284768002001820037200371842273187451010020010000200200002003720037111020110099100100100001000090007101161119791100001002003820038200382003820038
102042003715001031968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820135
1020420037150061196872510100100100001001000050028476800200182003720037184220318745101002021000020020000200372003711102011009910010010000100021800007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000000007101161120034100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03090b18191e1f3f4e51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611965425100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000001206402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000011206402162219785010000102003820038200382003820038
10024200371500000006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000001506402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000306402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmin d0, d8, d9
  fmin d1, d8, d9
  fmin d2, d8, d9
  fmin d3, d8, d9
  fmin d4, d8, d9
  fmin d5, d8, d9
  fmin d6, d8, d9
  fmin 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)03191e3f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000651102161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010001351101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010006051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100004251101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010003186851101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000351101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100027351101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191f3f51inst 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)5f60696b6d6edispatch 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150003925800101080000108000050640000012001902003820038999631001880010208000020160000200382003811800211091010800001003502000071600085200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000012001902003820038999631001880010208000020160000200382003811800211091010800001003502000061600046200350080000102003920039200392019120039
80024200381500070425800101080000108000050640000012001902003820038999631001880010208000020160000200382003811800211091010800001000502000071600065200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000012001902008920038999631001880010208000020160000200382003811800211091010800001000502000041600067200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000012001902003820038999631001880010208000020160000200382003811800211091010800001003502000071600057200350080000102003920039200392003920039
8002420038150003925800101080000108000050640000012001902003820038999631001880010208000020160000200382003811800211091010800001000502000061600066200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000120019020038200389996310018800102080000201600002003820038118002110910108000010066502000052800066200350080000102003920039200392003920039
800242003815011043925800101080000108000050640000012001902003820038999631001880010208000020160000200382003811800211091010800001003502000061600077200350080000102003920039200392008720039
80024200381501035025801051280000108000050640000012001902003820038999631001880010208000020160000200382003811800211091010800001000502000071600065200350080000102003920039200392003920039
80024200381500039258001010800001080000506400000120019020038200389996310018800102080000201600002003820038118002110910108000010012502000081600075200350080000102003920039200392003920039