Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMU (scalar, S to S)

Test 1: uops

Code:

  fcvtmu 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)0304080b18191e1f3a3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000000026225472510001000100039816013018303730372414328951000100010003037303711100110000000000077416442629100030383038303830383038
1004303724100000026225472510001000100039816003018303730372414328951000100010003037303711100110000000100077416442629100030383038303830383038
1004303724100000026225472510001000100039816003018303730372414328951000100010003037303711100110000000000077416442629100030383038303830383038
1004303723000000026225472510001000100039816013018303730372414328951000100010003037303711100110000000000077416442629100030383038303830383038
1004303723100000026225472510001000100039816003018303730372414328951000100010003037303711100110000000000077416442629100030383038303830383038
10043037231000000210825472510001000100039816013018303730372414328951000100010003037303711100110000000100077416442629100030383038303830383038
1004303723100000026225472510001000100039816003018303730372414328951000100010003037303711100110000000000077416442629100030383038303830383038
1004303723100000026225472510001000100039816003018303730372414328951000100010003037303711100110000000000077416442629100030383038303830383038
1004303723100000028525472510001000100039816003018303730372414328951000100010003037303711100110000000000077416442629100030383038303830383038
1004303724100000026225472510001000100039816013018303730372414328951000100010003037303711100110000000100077416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtmu 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): 3.0037

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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000450612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716013001830037300372826432874510100200100002041000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000300612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037232000240612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037232000330612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372330003510612954725101001001000010010000500427716003001830037300372826432874510100200100002001018230037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003723300060892954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037233000510612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071042511296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037242006129538251001010100001010000504277160030018030037300372828632876710010201000020100003003730132111002110910101000010006402162229629010000103003830038300383003830038
1002430037233006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037224006129547251001010100241010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030090030037300372828632876710010201000020100003003730037111002110910101000010006403163229629010000103008530038300863003830038
1002430037224066129547431001911100001010000504277160030054030037300372828632876710010201000020100003003730037111002110910101000010106402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtmu s0, s8
  fcvtmu s1, s8
  fcvtmu s2, s8
  fcvtmu s3, s8
  fcvtmu s4, s8
  fcvtmu s5, s8
  fcvtmu s6, s8
  fcvtmu 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)03070a0b181e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611550000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100010811151200160020036800001002004020040200402004020040
802042003915500000512580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003916100000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001211151180160020036800001002004020040200402004020040
8020420039155000012302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000311151180160020036800001002004020040200402004020040
8020420039155000007225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001811151180160020036800001002004020040200402004020040
802042003915600000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000611151180160020036800001002004020040200402004020040
8020420039155000003152580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000611151180160020036800001002004020040200402004020040
802042003915500001230258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100010211151180160020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000911151180160120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b191e3f51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039156000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020639542003680000102004020040200402004020040
8002420039156000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020416452003680000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020516542003680000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020416452003680000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020516552003680000102004020040200402004020040
8002420039156000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020516552003680000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020516452003680000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020801322080000200392003911800211091010800001000005020516542003680000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020416542003680000102004020040200402004020040
8002420039155000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000005020516552003680000102004020040200402004020040