Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT32Z (vector, 4S)

Test 1: uops

Code:

  frint32z 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)03070a1e3a3f4e51inst 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
1004303723110220225472510001000100039816013018303730372414328951000100010003037303711100110002077416442629100030383038303830383038
1004303723111229625472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303724110227325472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303723111826825472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303724110211025472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303723110213125472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
100430372311026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
100430372311026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
100430372411026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303723110228425472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint32z 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)03080b1e1f3a3f4e51inst 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)9fa0a1a8accfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300000103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116011296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000003710116011296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116011296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116011296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116011296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116011296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116011296334100001003013330137301313008630038
1020430037233111044208161295472510100100100001001030060642798640300183003730037282713287621010020810331204101673008530085211020110099100100100001000010710116011296330100001003003830038300383003830038
102043003723300000254295472510100111100081001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116011296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161512296330100001003003830038300383003830038

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)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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300000019329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402163229629010000103003830038300383003830038
10024300372330000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402163229629010000103003830038300383003830038
100243003723300000018929547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372320000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402163229629010000103003830038300383003830038
10024300372330000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000906402162229629010000103003830038300383003830038
10024300372330000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372330000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372330000006129547251001010100001010000504277160130018300373003728291328767100102010000201000030037300371110021109101010000100000006402163229629010000103003830038300383003830038
10024300372320000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
10024300372330000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint32z v0.4s, v8.4s
  frint32z v1.4s, v8.4s
  frint32z v2.4s, v8.4s
  frint32z v3.4s, v8.4s
  frint32z v4.4s, v8.4s
  frint32z v5.4s, v8.4s
  frint32z v6.4s, v8.4s
  frint32z 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): 0.2506

retire (01)cycle (02)03080b18191e1f243f51inst 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)9d9fa0a1a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491550000150058258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000030111511801600200360800001002004020040200402004020040
8020420039155000060072258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000030111511801600200360800001002004020040200402004020040
8020420039156000060030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040
8020420039156000000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040
8020420039156000000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040
8020420039155000090030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800000100000000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa8accfd0d5d6dbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550102082258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502001616017720036080000102004020040200402004020040
800242003915500040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502001716017620036080000102004020040200402004020040
8002420039156030402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020014160171720036080000102004020040200402004020040
800242003916109040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000502001716017820036080000102004020040200402004020040
8002420039156042040518001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001010502008160171720036080000102004020040200402004020040
80024200391550120402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020014160151520036080000102004020040200402004020040
8002420039156015040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001004755020017160161620036080000102004020040200402004020040
8002420039155015040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502001716017820036080000102004020040200402004020040
80024200391550210402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020017160161620036080000102004020040200402004020040
800242003915502730402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020814160171720036080000102004020040200402004020040