Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTA (scalar, D)

Test 1: uops

Code:

  frinta 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073316232629100031323038303830383038
10043037250302254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073316222629100030383038303830383038
10043037231261254725100010001000398160030183037303724143289510001000100030373037111001100000073316332629100030383038303830383038
10043037230149254725100010001000398160030183037303724143289510001000100030373037111001100000073316332658100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073216332629100030383038303830383038
10043037230103254725100010001000398160030183037303724143289510001000100030373037111001100000073316332629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100010073416332629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073216332629100030383038303830383038
1004303724069254725100010001000398160030183037303724143289510001000100030373037111001100010073316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinta 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): 3.0037

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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723310000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300000000642954725101251251000012510000626427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000003075811611296330100001003003830038300383003830038
1020430037233000001200892954725101251001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021713296330100001003003830038300383003830038
10204300372320000000018929547101101001251000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300000000612954725101001001000010010000500427716003001830037300372826432874510729200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723200000001612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037233010000001032954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000003071411621296330100001003003830038300383003830038
1020430037233000000001102954725101001251000012510000626427716013001830037300372826432874410125200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300022288192026132952862101251221002413210300587427986403001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723200000000612954725101001251000010010150500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)60696b6d6edispatch 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)91inst 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
100243003722500612954725100171010000101000050427716003001803003730037282863287671001020100002010000300373003711100211090101010000100000640216222962910000103003830038300383003830038
10024300372250511032954725100101010000101000050427716013001803003730037282863287671001020100002010000300373003711100211090101010000100100640216222962910000103003830038300383003830038
1002430037225003072954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211090101010000100100640224222966710000103003830038300383003830086
1002430037225012612954725100101010000101000071427716003001803003730037282863287861001020100002010000300373003711100211090101010000102100640216222962910000103003830038300383003830038
1002430037225001032954725100101010000121015050427716003001803003730084282863287671001020100002010000300373003711100211090101010000100000640216222962910000103003830038300383003830038
10024300372250121032954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211090101010000100000640216222962910000103003830038300383003830038
10024300372250121032954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211090101010000100000640216222962910000103003830038300383003830038
100243003722400612954725100101010000101000055427716003001803003730037282863287671001020100002010000300373003711100211090101010000100000640239522962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211090101010000100000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211090101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinta d0, d8
  frinta d1, d8
  frinta d2, d8
  frinta d3, d8
  frinta d4, d8
  frinta d5, d8
  frinta d6, d8
  frinta d7, d8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03070a0e181e3f51inst 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)9fa6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491561100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
8020420039155110042630258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915511000309258010810080008100800205006401320200202003920039997769990801202028003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
80204200391551100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151181161120036800001002004020040200402004020040
80204200391551100030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
80204200391551100072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
80204200391551100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915611002130258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010011151181161120036800001002004020040200402004020040
80204200391551100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
80204200391561100630258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa1a6a8aaaccdcficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015527040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200916752003680000102004020040200402004020040
800242003915560040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000900050200616562003680000102004020040200402004020040
8002420039155297040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200616462003680000102004020040200402004020040
8002420039155507040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000003050200416782003680000102004020040200402004020040
800242003915548040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200716752003680000102004020040200402004020040
80024200391600040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000132580050200716752003680000102004020040200402004020040
800242003915612040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000003050200416852003680000102004020040200402004020040
800242003915557040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200616642003680000102004020040200402004020040
800242003915654040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200616752003680000102004020040200402004020040
800242003915651040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000050200716772003680000102004020040200402004020040