Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTX (vector, 8H)

Test 1: uops

Code:

  frintx v0.8h, v0.8h
  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
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037222471625472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372208225472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintx v0.8h, v0.8h
  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)03080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400000120010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000010300071021622296330100001003003830038300383003830038
10204300372250016681661603420294981161017713910040130107506794286624130306301823042528289402883811345226114912221133030416304189110201100991001001000010020022222303400889480342990039100001003036830420304203042130420
102043045522700089107779215823294741781021114010064145112006984287976130342304123041828302472891211341224111642211116530403303678110201100991001001000010002202218898000871489232992135100001003041530418304193027630464
10204303202280108912007920117552947517410196134100641471135069542879761303423023030463282913928855113502301131922211323304583045510110201100991001001000010002201011075000912280342997937100001003046630464304183042130230
1020430465228100881209704052432952018910209148100641441045076742879761301983041730466282903128871110362281066122110996302293032381102011009910010010000100000010300071021622296330100001003003830038300383003830038
10204300372250000012006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000010300071021622296330100001003003830038300383003830038
102043003722500000120076829547251010010010000100100005004278512130018300373013228264328745101002001000020010000300853003721102011009910010010000100000000282100075821622296330100001003003830038300383003830038
10204300372250000012008229547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000300071021622296330100001003003830038300383003830038
102043003722400000120010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000010300071021622296330100001003003830038300383003830038
102043003722500000120010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000300071021622296330100001003003830038300383003830038

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)9fa6a8acc2cdcficache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100100064002162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100130064002162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
100243003722400000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282860328767100102010000201000030037300371110021109101010000100000064002162229629010000103008530038300383003830038

Test 3: throughput

Count: 8

Code:

  frintx v0.8h, v8.8h
  frintx v1.8h, v8.8h
  frintx v2.8h, v8.8h
  frintx v3.8h, v8.8h
  frintx v4.8h, v8.8h
  frintx v5.8h, v8.8h
  frintx v6.8h, v8.8h
  frintx v7.8h, v8.8h
  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)03070a1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391501112722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001611151181161120036800001002004020115201012004020040
80204200391501112722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001003011151181161120036800001002004020040200402004020040
8020420039150110722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001002311151181161120036800001002004020040200402004020040
8020420039150113302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001005311151181161120036800001002004020040200402004020040
80204200391501112302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001004011151181161120036800001002004020040200402004020040
80204200391501112722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001004311151181161120036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001001011151181161120036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001001611151181161120036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001002011151181161120036800001002004020040200402004020040
8020420039150110302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001002011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa1a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000060225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000450050201016352003680000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100063005020516742003680000102004020040200402004020040
800242003915000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000126005020416532003680000102004020040200402004020040
800242003915000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000129005020616532003680000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000114005020516532003680000102004020040200402009320040
80024200391500000402580010108000010800005064000002008320039200399996310019800102080000208000020039200391180021109101080000100093005020416462003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000141005020516642003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000138005020316542003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000150005020316562003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000144005020316352003680000102004020040200402004020040