Apple M1 Microarchitecture Research by Dougall Johnson

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

FACGT (scalar, D)

Test 1: uops

Code:

  facgt 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)0308091e1f3f4e51inst 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)a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
100420371500120611687251000100010002646801201820372037157231895100010002000203720371110011000000373216221787100020382038203820382038
100420371500001031687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037160000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038
10042037150000611687251000100010002646801201820372037157231895100010002000203720371110011000000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  facgt 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)030818191e1f3f4e51inst 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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007103161119791100001002003820038200382003820038
1020420037150000009001968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715010000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010001007101161119791100001002003820038200382003820038

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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119687251001010100001310000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006404163419785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100106403164419785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100106403164419785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100106404163419785010000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010001116403163419785010000102003820038200382003820038
1002420037150044119687251001010100241010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100036404164319785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100036403164319785110000102013120086200862003820038
1002420037150061196872510010101000010100005028476801200542003720037184443187671001020100002020000200372003711100211091010100001000906403163419785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006404164419785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006404163419785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  facgt 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)033f4e51inst 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
102042003715061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000217101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680120018200372003718422318745102592001000020020000200372003711102011009910010010000100067101161119791100001002003820038200382003820038
10204200371508419687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100137101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010001717101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100006162847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100037101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100307101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100407101161119791100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000003006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000100006402162219785010000102003820038200382003820038
100242003715000000006119687801001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000100006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000200006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000016402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010152502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000100006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000100006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000103006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  facgt d0, d8, d9
  facgt d1, d8, d9
  facgt d2, d8, d9
  facgt d3, d8, d9
  facgt d4, d8, d9
  facgt d5, d8, d9
  facgt d6, d8, d9
  facgt 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)030b18191e1f3f51inst 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
80204200571500000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103162220035800001002003920039200392003920039
802042003815000000124258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381500000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815000000103258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815000000515258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381500000082258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815000000105258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815000000103258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815100000168258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815000000124258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)5f60696d6edispatch 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)9fa8accfd0icache miss (d3)d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915011412580010108000010800005064000000200192003820038100053100188001020800002016000020038200381180021109101080000100050200091671720035080000102003920039200392003920039
80024200381503925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020001716171720035080000102003920039200392003920039
80024200381503925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010005020001716171720035080000102003920039200392003920039
80024200381501232580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502000171671720035080000102003920039200392003920039
800242003815039100800101080000108000050640000012001920038200389996310018801122080000201600002003820038118002110910108000010005020001716171720035080000102003920039200392003920039
800242003815015012580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502000171617720035080000102003920039200392003920039
800242003815016925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020001716171720035080000102003920039200392003920039
800242003815081258001010800001080000506400000120019200892003899963100188001020800002016000020038200381180021109101080000100050200081661720035080000102003920039200392003920039
800242003815012525800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010005020001716171720035080000102003920039200392003920039
800242003815039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100050200061661720035080000102003920039200392003920039