Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT32X (vector, 2S)

Test 1: uops

Code:

  frint32x 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)031e3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100430372400932547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037231201032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724011032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724001262547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303724001242547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint32x 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)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710011611296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710011611296330100001003003830038300383003830038
10204300372330000021061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000739011611296330100001003003830038300383003830038
10204300372330002000357295472510100100100001001000050042785121300183003730037282643287451010020010000200100003003730037111020110099100100100001000001000710011611296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710011611296330100001003003830038300383003830038
1020430037232000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710011611296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710011611296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710011611296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000710011611296330100001003003830038300383003830038
1020430037232000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020210099100100100001000000000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372247506129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225273010329547251001010100001010000504277423030018300373003728286328767100102010000201000030037300371110021109101010000100306402162229629110000103003830038300383003830038
10024300372251506129547251001010100001010148504277160030018300373003728286328767101622010000201000030084300371110021109101010000100006404162229629010000103003830038300383003830038
1002430037225306129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722530010329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372252106129547431001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint32x v0.2s, v8.2s
  frint32x v1.2s, v8.2s
  frint32x v2.2s, v8.2s
  frint32x v3.2s, v8.2s
  frint32x v4.2s, v8.2s
  frint32x v5.2s, v8.2s
  frint32x v6.2s, v8.2s
  frint32x 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)030a0b1e1f3a3f51inst 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)9fa0a1a8a9acb5c5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581550000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100006000111511811620036800001002004020040200402004020040
80204200391550000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511801620036800001002004020040200402004020040
802042003915600000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000300111511801620036800001002004020040200402004020040
80204200391610000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511801620036800001002004020040200402004020040
80204200391610000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100008000111511801620036800001002004020040200402004020040
802042003915600600302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000059000111511801620036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000330111511801620036800001002004020040200402004020040
8020420039155000001170258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111514601620036800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511801620036800001002004020040200402004020040
802042003915500000616258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001000111511801620036800001002004020040200402004020247

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b1e1f3f51inst 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)9fa1a8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039156000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050201416015152003680000102004020040200402004020040
80024200391600001204025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050201516016132003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050201716016132003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050201616012162003680000102004020040200402004020040
8002420039156001004025800101080000108000050640000120020200392003999963100198001020800002080106200392003911800211091010800001000350201316013112003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999968100198001020800002080000200392003911800211091010800001000050201616012162003680000102004020040200402004020040
80024200391610000040258001010800001080000506400000200202003920039100063100198001020800002080000200392003911800211091010800001000050201416019132003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050201316014162003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000650201716013132003680000102004020040200402004020040
8002420039161000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000350201416011112003680000102004020040200402004020040