Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTM (vector, 4S)

Test 1: uops

Code:

  frintm v0.4s, 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)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
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100002073116212629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100010073116212629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
10043037231284254725100010001000398160130183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
10043037243157254725100010001000398160030183037303724143289510001000100030373037111001100000073116212629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116212629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintm v0.4s, 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)03080b0e18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723200000000612954725101001001000010010000500427716003001830037300372826432876210100200100002001000030037300371110201100991001001000010000000000710216112963300100001003003830038300383003830038
1020430037233000000002512954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
102043003723200000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
102043003723300000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
102043003723300000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
102043003723200000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
1020430037233000000003462954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
1020430037233000001200612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
102043003723300000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710116112963300100001003003830038300383003830038
102043003723300000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000710126112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201054330037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225000394129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372240006129547251001012100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250008229547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000120640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintm v0.4s, v8.4s
  frintm v1.4s, v8.4s
  frintm v2.4s, v8.4s
  frintm v3.4s, v8.4s
  frintm v4.4s, v8.4s
  frintm v5.4s, v8.4s
  frintm v6.4s, v8.4s
  frintm v7.4s, 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)03080b18191e1f3f51inst 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)9fa0a6a8a9acc5branch mispredict (cb)cdcfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058155000018058258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016000200360800001002004020040200402004020040
8020420039156000018030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016000200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000031115118016000200360800001002004020040200402004020040
80204200391550000219030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001001115118016000200360800001002004020040200402004020040
802042003915601006030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016000200360800001002004020040200402004020040
80204200391550000477072258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016010200360800001002004020040200402004020040
8020420039155000033030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016000200360800001002004020040200402004020040
80204200391560000384030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016000200360800001002004020040200402004020040
802042003915500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016511200460800001002004020040200402004020040
80204200391560000156030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016000200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa1a6a7a8accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915600003630040258001010800001080000506400001020020200392003999963100198001020800002080000200392009011800211091010800001000000502000181616620036080000102004020040200402004020040
800242003915600009006325800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000050205161661620036080000102004020040200402010220040
800242003916100005700103258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000113502000161651620036080000102004020040200402004020040
800242003915500003270040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000000502000161661620036080000102004020040200402004020040
8002420039155000000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000502053616161620036080000102004020040200402004020040
8002420039155000030600402580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010000005020001516161620036080000102004020040200402004020040
8002420039155000000040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000000502000161616620036080000102004020040200402004020040
80024200391550000261004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000050200061661620036080000102004020040200402004020040
8002420039155000000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000000502053161661620036080000102004020040200402004020040
800242003915600003004025800101080000108000050640000052002020039200399996310019800102080000208000020039200391180021109101080000100000050200061661620036080000102004020040200402004020040