Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64Z (vector, 2S)

Test 1: uops

Code:

  frint64z v0.2s, v0.2s
  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
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222701100030383038303830383038
100430372496125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038307430383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64z v0.2s, v0.2s
  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)030818191e3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500007262954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000625427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372240000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
102043003722500068342954725101001001000010010000500427716003001833003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372250000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038
10204300372240000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e3f4e51inst 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)6061696b6d6edispatch 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)9fa8acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003730100144612954725100101010000101000050427716010300180300373003728286328767100102010000201000030037300371110021109101010000100006400216222962910000103003830038300383003830038
10024300372330030612954725100101010000101000050427716000300180300373003728286328767100102010000201000030037300371110021109101010000101006400216222962910000103003830038300383003830038
10024300372330048612954725100101010000101000050427716010300180300373003728286328767100102010000201000030037300371110021109101010000100006400216222962910000103003830038300383003830038
1002430037233000612954725100101010000101000050427716000300183300373003728286328767100102010000201000030037300371110021109101010000100006400216222962910000103003830038300383003830038
10024300372320012612954725100101010000101000050427716010300180300373003728286328767100102010000201000030037300371110021109101010000100006400316222962910000103003830038300383003830038
1002430037233106612954725100101010000101000050427716015300180300373003728286328767100102010000201000030037300371110021109101010000100306400216222962910000103003830038300383003830038
1002430037232000612954725100101010000101000050427716000300180300373003728286328767100102010000201000030037300371110021109101010000100006400216222962910000103003830038300383003830038
1002430037233000612954725100101010000101000050427716000300180300373003728286328767100102010000201000030037300371110021109101010000101006400216222962910000103003830038300383003830038
1002430037232006612954725100101010000101000050427716000300180300373003728286328767100102010000201000030037300371110021109101010000100006400216222962910000103003830038300383003830038
1002430037233006612954725100101010000101000050427716005300180300373003728286328767100102010000201000030037300371110021109101010000100006405216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint64z v0.2s, v8.2s
  frint64z v1.2s, v8.2s
  frint64z v2.2s, v8.2s
  frint64z v3.2s, v8.2s
  frint64z v4.2s, v8.2s
  frint64z v5.2s, v8.2s
  frint64z v6.2s, v8.2s
  frint64z v7.2s, v8.2s
  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)0308181e1f3f51inst 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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039150000030258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
8020420039150000061125801081008000810080020500640132020020020039200399977069990801202008003220080032200392003911802011009910010080000100147011151351161120089800001002004020040200402009220040
8020420039155111688851258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
8020420039150000072258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151711161120036800001002004020040200402004020040
80204200391500000114258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391500000114258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150000051258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391500000135258010810080008100800205006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001000311151181161120036800001002004020040200402004020040
8020420039150000093258010810080008100800245006401320200200200392003999770699908012020080032200800322003920039118020110099100100800001001311151181161120036800001002004020040200402004020040
8020420039150000072258010810080008100800205006401320200200200392003999770699848012820080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b181e3f51inst 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)9fa6a8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115600040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001550203160112003680000102004020040200402004020040
80024200391560004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050201160112003680000102004020040200402004020040
80024200391560004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050201160222003680000102004020040200402004020040
80024200391550004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050201160112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050201160112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050201160222003680000102004020040200402004020040
80024200391550004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050202160112003680000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050201160112003680000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198012220800002080000200392003911800211091010800001000050201160222003680000102004020040200402004020040
800242003916000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001250201160112003680000102004020040200402004020040