Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTA (vector, 4S)

Test 1: uops

Code:

  frinta 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)031e1f3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037231206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112703100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037231206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinta 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)031e3f4e51inst 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)9fa0a1a8a9acc2c9cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037232061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037232061295474410100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000300071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071021622296330100001003003830086300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)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)9fa0a1a6a8a9acc2cfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000000064041606529629010000103003830038300383003830038
10024300372400000009008929547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000000064051605629629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000000064061606529629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018300373003728286032878610010201000020100003003730037111002110910101000010000100064061605429701310000103003830038300383008430038
1002430037225000000028806129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000000064051605529629010000103003830038300383003830168
10024300372250000000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000300064051606629629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730070111002110910101000010000400064051606629629010000103003830038300383003830038
100243003722500000000056729547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000000064061606629629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000000064061606629629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000000064061606629629010000103003830085300383007930038

Test 3: throughput

Count: 8

Code:

  frinta v0.4s, v8.4s
  frinta v1.4s, v8.4s
  frinta v2.4s, v8.4s
  frinta v3.4s, v8.4s
  frinta v4.4s, v8.4s
  frinta v5.4s, v8.4s
  frinta v6.4s, v8.4s
  frinta 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)030708090b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118116002003600800001002004020040200402004020040
80204200391560000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000010001115118816002003600800001002004020040200402004020040
80204200391550000000030258010810080008100800205006409640200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391560000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391560000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040
80204200391550000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000001115118016002003600800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa8acc2cfd2icache miss (d3)d5d6d9daddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015500008925800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000101305020707160057200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020105160077200360080000102004020040200402004020040
800242003915511904025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020007160056200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020007160064200360080000102004020040200402004020040
8002420039155000055725800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020007160056200360080000102004020040200402004020040
800242003915600004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020007160057200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000100005020008160075200360080000102004020040200402004020040
800242003915500004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020207160057200360080000102004020040200402004020040
800242003915600004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020107160075200360080000102004020040200402004020040
800242003915510004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000100005020105160057200360080000102004020040200402004020040