Apple M1 Microarchitecture Research by Dougall Johnson

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

FMAXV (4S)

Test 1: uops

Code:

  fmaxv s0, v0.4s
  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)696d6edispatch 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
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073216112629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
100430372206125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116122629100030383038303830383038
1004303723010525472510001000100039816030183037303724143289510001000100030373037111001100000373216212629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037221240325472510001000100039816030183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
100430372306125472510001000100039816030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fmaxv s0, v0.4s
  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)030b1e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250001242954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250001662954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372240001242954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300822240002312954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372240001702954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225000842954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250001932954725101001001000010010000561427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250001912954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110202100991001001000010000071011611296330100001003003830038300383003830038
10204300372250001492954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071001611296330100001003003830038300383003830038
10204300372240002122954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)72scheduler 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500090612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722400000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000003006402162229629010000103003830038300383003830038
100243003722400000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722400000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162129629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716030018300373003728286032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fmaxv s0, v8.4s
  fmaxv s1, v8.4s
  fmaxv s2, v8.4s
  fmaxv s3, v8.4s
  fmaxv s4, v8.4s
  fmaxv s5, v8.4s
  fmaxv s6, v8.4s
  fmaxv s7, v8.4s
  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)031e3f51inst 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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182161220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162120036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220280032200392003911802011009910010080000100011151182162120036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151180162220036800001002004020040200402004020040
8020420039150012525801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182161220036800001002004020040200402004020040
802042003915005125801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162120036800001002004020040200402004020040
802042003915005125801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182161220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151181161220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100011151182162120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3f51inst 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)9fa1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020517772003680000102004020040200402004020040
8002420039150000000001262580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020716752003680000102004020040200402004020040
800242003915000000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020716752003680000102004020040200402004020040
800242003915000000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020516752003680000102004020040200402004020040
800242003915000000000612580010108000010800005064000012002020039200399996310019801262080000208000020039200391180021109101080000100000005022716572003680000102004020040200402004020040
800242003915000000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020516572003680000102004020040200402004020040
8002420039150000000001032580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020616572003680000102004020040200402004020040
800242003915000000000822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020716752003680000102004020040200402004020040
8002420039150000000001452580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020716752003680000102004020040200402004020040
8002420039150000000001452580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020516572003680000102004020040200402004020040