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, S)

Test 1: uops

Code:

  fneg s0, s0
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  fneg s0, s0
  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)03080b18191e3a3f4e51inst 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)9fa0a1a6a7a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000300611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000300611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
102042003715000002790611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000060611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000240611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000009641968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000075411611197960100001002003820038200382003820038
102042003715000005370611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371500000240611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038

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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000240006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006403162219786010000102003820038200382003820038
100242003715000009006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000036006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
10024200371500000528006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000306402162219786010000102003820038200382003820038
1002420037150000000025319686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000030006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000033006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000012006119686251001010100001010000502847521020018200372008418443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000018006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fneg s0, s8
  fneg s1, s8
  fneg s2, s8
  fneg s3, s8
  fneg s4, s8
  fneg s5, s8
  fneg s6, s8
  fneg s7, s8
  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)03181e1f3f51inst 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)9fa0a1a8c5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150057029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801620035800001002003920039200392003920039
80204200381500111029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003841802011009910010080000100000111511801620035800001002003920039200392003920039
80204200381500270140258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801620035800001002003920039200392003920039
8020420038150024029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801620035800001002003920039200392003920039
8020420038150021029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100002111511801620035800001002003920039200392003920039
8020420038150021029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801620035800001002003920039200392003920039
80204200381500180758258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801620035800001002003920039200392003920039
8020420038150460124258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801620035800001002003920039200392003920039
802042003814906017629258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801620035800001002003920039200392003920039
802042003815003071258010810080008100800205006401320200192003820038997769989801202008003220080032200382003821802011009910010080000100000111511801620035800001002003920039200392003920039

1000 unrolls and 10 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)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)9fa1a8a9cfd0d2d5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511504333925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
80024200381500651425800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
80024200381500123925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039
8002420038150093925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100605020001161120035080000102003920039200392003920039
8002420038150003925800101080000108000050640000102001920038200389996310018800102080000208000020038200381180021109101080000100005020001161120035080000102003920039200392003920039