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, 2D)

Test 1: uops

Code:

  frinta v0.2d, v0.2d
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724310325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308425472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723012425472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723015925472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinta v0.2d, v0.2d
  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)9fa0a6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000240612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003008530038300383003830038
102043003723300000612954725101001001000010010000500427716013002230037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723200000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000036061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372240000165061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
1002430037225000042061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000026403163329629010000103003830038300383003830038
10024300372330000690117295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110022109101010000100000006403163329629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
100253003722500000061295292510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinta v0.2d, v8.2d
  frinta v1.2d, v8.2d
  frinta v2.2d, v8.2d
  frinta v3.2d, v8.2d
  frinta v4.2d, v8.2d
  frinta v5.2d, v8.2d
  frinta v6.2d, v8.2d
  frinta v7.2d, v8.2d
  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)03080918191e1f3a3f51inst 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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060161000000058258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
80204200391550000120030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811621200360800001002004020040200402004020040
8020420039156000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
8020420039156000000030258010810080008100800205006401321200202007520039997769990801202008003220080032200392003911802011009910010080000100000000111511821611200360800001002004020040200402004020040
8020420101155000030030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
802042003915500001020030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811611200360800001002004020040200402004020040
802042003915500000038429258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511811611200360800001002004020040200402004020040
80204200391550000120030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511811611200360800001002004020114200402004020040
8020420039155000000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511811611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3a3f51inst 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)5f60696d6edispatch 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)9fa1a8acc2cfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040156002724525800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502401616171420036080000102004020040200402004020040
800242003915500024525800101080000108000050640000112002020039200399996310019800102080000208000020039200391180021109101080000100000502401416171020036080000102004020040200402004020040
80024200391550002452580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010010450243131682120036080000102004020040200402004020040
8002420039155003024525801081080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502401616181720036080000102004020040200402004020040
800242003916100024525800101080000108000050640000112002020039200399996310019800102080000208000020039200391180021109101080000100000502401216201920036080000102004020040200402004020040
8002420039155004828725800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000502401416101920036080000102004020040200402004020040
800242003915600024525800101080000108000050640000112002020039200399996310019800102080000208000020039200391180021109101080000100000502401316161720036080000102004020040200402004020040
8002420039155000245258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005024017161919200361580000102004020040200402004020040
8002420039155001224551800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000502401216181820036080000102004020040200402004020040
800242003915500024525800101080000108000050640000112002020039200399996310019800102080000208000020039200391180021109101080000100000502401416151220036080000102004020040200402004020040