Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINP (scalar)

Test 1: uops

Code:

  fminp d0, v0.2d
  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)03191e3f4e51inst 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
1004203715006116862510001000100026452112018203720371571318951000100020002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100020002037203711100110003073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100020002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100020002037203711100110000073116111786100020382038203820382038
10042037150010516862510001000100026452112018203720371571318951000100020002037203711100110000073116111786100020382038203820382074
1004203715106116862510001000100026452112018203720371571318951000100020002037203711100110002373116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100020002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100020002037203711100110002373116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100020002037203711100110001073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100020002037203711100110001373116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fminp d0, 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)030b18191e1f3f4e51inst 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
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002002000020037200371110201100991001001000010031727101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000061196862510100100100001001000050028475210200182003720037184213187451010020010000200200002008520037111020110099100100100001002437101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500000053619686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002850049120018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382008620038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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
1002420037150906119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001037153640216221978610000102003820038200382003820038
100242003715021061196862510010101000010100005028475212001820037200371844331876710010201000020200002003720037111002110910101000010220640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003721100211091010100001000640216221978610000102008620038200382003820038
10024200371501029886119686251001010100001010000502847521200182003720037184433187671001020100002020674200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000202000020037200371110021109101010000100123640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521200182003720037184433187671001020100002020000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fminp d0, v8.2d
  fminp d1, v8.2d
  fminp d2, v8.2d
  fminp d3, v8.2d
  fminp d4, v8.2d
  fminp d5, v8.2d
  fminp d6, v8.2d
  fminp d7, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b181e3f51inst 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)9fa1a8a9acc5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500002925801081008000810080020500642480200192003820038997769989801202008003220016006420038200381180201100991001008000010000051111511816020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420038150000298580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420038150005342925801081008000810080020500640132200192003820038997769989801202008003220016006420038200381180201100991001008000010000018111511816020035800001002003920039200392003920039
802042003815000059925801081008000810080020500640132200192003820038997769989801202008003220016006420038200381180201100991001008000010001003111511816020035800001002003920039200392003920088
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000109111511816220035800001002003920039200392003920039
8020420038150000712580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
8020420090150000292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000003111511816020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401322001920038200389977699898012020080032200160064200382003811802011009910010080000100000722111511816020035800001002003920039200392024220039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322001600642003820038118020110099100100800001000000111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3a3f51inst 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)9fa0a1a6a8a9aaacc2cfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500000000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000000502091606220035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000012005820038200381000531001880010208000020160000200382003811800211091010800001000000030502021606220035080000102003920111200992003920039
80024200381500000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021602620035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021602620035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000010030502021602220035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000120502061606220035080000102003920039200392003920039
800242003815000000000392580010108000010800005064000002001920038200381000431001880010208000020160000200382003811800211091010800001000000060502031603620035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502021602220035080000102003920039200392003920039
80024200381500000000039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000502061606220035080000102003920039200392003920039
8002420038150000000002102580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000520030502021602220035080000102003920039200392003920039