Apple M1 Microarchitecture Research by Dougall Johnson

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

FNEG (scalar, D)

Test 1: uops

Code:

  fneg d0, d0
  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)a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715961168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fneg d0, 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)03080918191e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000606119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521200182003720037184213187451010020010000210100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000156119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002008520037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000002346119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640316221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150001561196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001003640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500039130196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150002161196862510010101000010100005028475211200542003720037184433187671001020100002010000200372003711100211091010100001000640216221984710000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fneg d0, d8
  fneg d1, d8
  fneg d2, d8
  fneg d3, d8
  fneg d4, d8
  fneg d5, d8
  fneg d6, d8
  fneg d7, d8
  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)03070a18191e1f3f51inst 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)9fa6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500000690292580108100801081008002050064013220066200382003899776100148012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011000052258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000003011151181161120035800001002003920039200392003920039
802042003815011000029258010810080008100800205006424642005720038200989977699898012020080032200800322003820038118020110099100100800001000000411151181161120035800001002003920039200392003920039
802042003815011000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815011000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
8020420038150110012071258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000100011151181161120035800001002003920039200392003920039
802042003815011000029818010810080008100804135006401322001920038200389977699898012020080032200800322008720038118020110099100100800001000100011151181161120035800001002003920039200392003920039
802042003815011000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308091e3f51inst 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)9facc5cfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500003950800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050202160122003580000102003920039200392003920039
8002420038150003213925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050201160122003580000102003920039200392003920039
80024200381500063925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039
80024200381500003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039
800242003815000051425800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039
80024200381500003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039
80024200381500003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039
80024200381500004525800101080000108000050640000112001920038200389996310018800102080000208000020038200381180021109101080000100050201162112003580000102003920039200392003920039
80024200381500003925800101080000108000050640000112001920038200389996310018800102080000208000020038200381180021109101080000100050203160112003580000102003920039200392003920039
8002420038150000229258001010800001080000506400000120019200382003899962710018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039