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, 2S)

Test 1: uops

Code:

  frint32z 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)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
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000075216222626100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073216212629100030383038303830383038
1004303724121682547251000100010003981603018303730372414328951000100010003037303711100110001075216222626100030383038303830383038
10043037230612547251000100010003981603018303730372413328951000100010003037303711100110000073116222629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116222629100030383038303830383038
100430372312612547251000100010003981603018303730372413328951000100010003037303711100110000073116222626100030383038303830383038
100430372407382547251000100010003981603018303730372413328951000100010003037303711100110000073216112629100030383038303830383038
100430372301562547251000100010003981603018303730372414328951000100010003037303711100110000073116122626100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073216112626100030383038303830383038

Test 2: Latency 1->2

Code:

  frint32z 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)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)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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372330000085295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300012061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372320000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372330001201825295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003724100000236029547251010010010008143103076804285272300183003730037282673288181025620010824226113743041630472511020110099100100100001000002249232838189212999438100001003032330517305653055230517
1020430565237011101329880788329465233102271541008812911650739429197930414305673056428302542894711962238117712361182530515305121211020110099100100100001002402301250868381223002629100001003059930568305163055930564
1020430610236151012068806043295022121023015310072144115007854289328303783047230512283034028873113422261132321610826304213022710110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003723300015061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723308629547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010020000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010200000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint32z v0.2s, v8.2s
  frint32z v1.2s, v8.2s
  frint32z v2.2s, v8.2s
  frint32z v3.2s, v8.2s
  frint32z v4.2s, v8.2s
  frint32z v5.2s, v8.2s
  frint32z v6.2s, v8.2s
  frint32z 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)031e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058155121392580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391550302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391550762580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391550752580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155012082580108100800081008002050064013220020200392003999769998680120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
80204200391561211082580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010010111511801600200360800001002004020040200402004020040
80204200391550302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
802042003915505052580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180202100991001008000010000111511801600200360800001002004020040200402004020040
80204200391610302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010003111511801600200360800001002004020040200402008920040
8020420039155121072580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b0e18191e1f3a3f51inst 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)9fa1a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500000001056258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020716452003680000102004020040200402004020040
80024200391550000000991258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000005020316452003680000102004020040200402004020040
800242003915500000001468258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000305020516532003680000102004020040200402004020040
80024200391550000000895258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020516462003680000102004020040200402004020040
80024200391560000000858258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316362003680000102004020040200402004020040
8002420039155000000082258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316362003680000102004020040200402004020040
80024200391550000000872258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316352003680000102004020040200402004020040
8002420039156000000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020716352003680000102004020040200402004020040
80024200391560000000853258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020316552003680000102004020040200402004020040
800242003915600000001020258001010800001080000506400001120020200392003999963100198001020800002080000200392003911800211091010800001000305020616352003680000102004020040200402004020040