Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTZ (vector, 4S)

Test 1: uops

Code:

  frintz 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
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100010073116112629100030383038303830383038
10043037231261254725100010001000398160030183037303724143289510001000100030373037111001100002282873116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722093254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722082254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372212103254725100010001000398160030183037303724143289510001000100030373037111001100010073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintz 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)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000120103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000060000710011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000200000710011611296330100001003003830038300383003830038
1020430037225000012010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000021120000710011611296330100001003003830038300383003830038
10204300372250000120822954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000002356680000733011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000130000710001611296330100001003003830038300383003830038
102043003722500001207682954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000002760000710011611296330100001003003830038300383003830038
10204300372250000001032954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000003260000710011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000230000710011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000200000710011611296330100001003003830038300383003830038
10204300372250000210103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000100000710011611296330100001003003830038300383003830038

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)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010233640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010103640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010269640216222962910000103003830038300383003830038
10024300372251053629547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010289640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010270640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010293640216222962910000103003830038300383003830038
1002430037224006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010233640216222962910000103003830038300383003830038
1002430037225009629547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010302779640216222962910000103003830038300813003830038
1002430037225008229547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010269640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010256640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintz v0.4s, v8.4s
  frintz v1.4s, v8.4s
  frintz v2.4s, v8.4s
  frintz v3.4s, v8.4s
  frintz v4.4s, v8.4s
  frintz v5.4s, v8.4s
  frintz v6.4s, v8.4s
  frintz 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)9fa1a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000001207225801081008000810080020500640132120020200392003999776999080120200800322008003220039202451180201100991001008000010001030111511801600200360800001002004020040200402004020040
802042003915010001207225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000030111511801600200360800001002004020040200402004020040
802042003915000001207225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
802042003915000001207225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001000111511801600200360800001002004020040200402004020040
802042003915000001207225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001030111511801600200360800001002004020040200402004020040
80204200391500000007225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000030111511801600200360800001002004020040200402004020040
802042003915000001203025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001030111511801600200360800001002004020040200402004020040
80204200391500000007225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001030111511801600200360800001002004020040200402004020040
802042003915000001207225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001030111511801600200360800001002004020040200402004020040
802042003915000001207225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001030111511801600200360800001002004020040200402004020040

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)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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150001052580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020516432003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020516442003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020416342003680000102004020040200402004020040
80024200391500011092580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020416442003680000102004020040200402004020040
8002420039150004202580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020516442003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020416442003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020316342003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020416442003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000005020416442003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000005020516442003680000102004020040200402004020040