Apple M1 Microarchitecture Research by Dougall Johnson

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

CLZ (vector, 8H)

Test 1: uops

Code:

  clz v0.8h, v0.8h
  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)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)a0a8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037151261168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  clz v0.8h, v0.8h
  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)03080b1e3f4e51inst 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)6061696d6edispatch 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)9fa6a7a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020210099100100100001000000710001161119791100001002003820038200382003820038
1020420037150006611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
10204200371500002511968625101001001000010010000500284752100200182003720037184213187451027020010000204100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
1020420037150100611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
1020420037149000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752100200182003720037184213187451010020010000200100002003720037111020110099100100100001000000710001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006403162219786010000102003820038200382003820038
10024200371500000000063819686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
1002420037150100000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000016402162219786010000102003820038200382003820038
1002420037150000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102008520038201802003820038
1002420037150000009008619686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
1002420037150000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
10024200371500100000025119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
1002420037150000000008219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038
1002420037150000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786110000102003820038200382003820038
1002420037150000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  clz v0.8h, v8.8h
  clz v1.8h, v8.8h
  clz v2.8h, v8.8h
  clz v3.8h, v8.8h
  clz v4.8h, v8.8h
  clz v5.8h, v8.8h
  clz v6.8h, v8.8h
  clz v7.8h, v8.8h
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03070a1e3f51inst 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)9fa1a6a7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151183163220035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181162220035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200801362003820038118020110099100100800001000001011151183163220035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151183163320035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151183162320035800001002011320039200392010020039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000003311151183162320035800001002003920039200392003920039
802042008815111029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001009000011151183163220035800001002003920039200392003920039
8020420038150119182258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151183163220035800001002003920039200392003920039
802042003815011029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000022251285235520045800001002005020050200492004920049
802042004815011075278010010080000100800005006400002002820047200479971699938010020080000200800002004720047118020110099100100800001000000011151207247620044800001002004820048200482004820048

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa0a1a8accfd2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500873925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000502000181616162003580000102003920039200392003920039
800242003815000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000050200016166162003580000102003920039200392003920039
80024200381500039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001000005020006161662003580000102003920039200392003920039
80024200381500427042580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000050200016161452003580000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000050200016165162003580000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000050200116161662003580000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000050201015166132003580000102003920039200392003920039
8002420038150003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000502000131616162003580000102003920039200392003920039
8002420038150003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000502000161616162003580000102003920039200392003920039
800242003815000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000050200016161662003580000102003920039200392003920039