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, 2S)

Test 1: uops

Code:

  frintx 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220103254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
10043037231261254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
10043037221261254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723961254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
10043037230156254725100010001000398160030183037303724143289510001000100030373037111001100011073216222629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000373216222629100030383038303830383038
10043037230103254725100010001000398160130183037303724143289510001000100030373037111001100050073216222629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintx 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)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000055929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003007430038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372250000000012429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037224000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000006129547251010010310000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038

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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225128692954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010100640316342962910000103003830038300383003830038
1002430037225121892954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010130640416432962910000103003830038300383003830038
100243003722501032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010130640416432962910000103003830038300383003830038
1002430037225121032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010100640216332962910000103003830038300383003830038
100243003722512612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640416342962910000103003830038300383003830038
1002430080224121032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640416442962910000103003830038300383003830038
100243003722512732954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010100640316342962910000103003830038300383003830038
1002430037225121032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010030640416342962910000103003830038300383003830038
1002430037225127682954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010130640416342962910000103003830038300383003830038
1002430037225181032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010130640416442962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintx v0.2s, v8.2s
  frintx v1.2s, v8.2s
  frintx v2.2s, v8.2s
  frintx v3.2s, v8.2s
  frintx v4.2s, v8.2s
  frintx v5.2s, v8.2s
  frintx v6.2s, v8.2s
  frintx 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)03081e1f3f51inst 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)9fa1a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815003810302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511811600200360800001002004020040200402004020040
80204200391500120302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
8020420039150000302580108100800081008002050064013202006120039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002019920040200402004020040
802042003915004350302580108100800081008002050064262402002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915005310302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000100111511801600200360800001002004020040200402004020040
802042003915004050302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915002580302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020200200402004020040
802042003915009264302580108100800081008002050064013212017820039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915003210302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801600200360800001002004020040200402004020040
802042003915003630302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511801620200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)5f6061696d6edispatch 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)9fa1a6a8a9accfd0d2d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000001200402580010108000010800005064000001020020200392003999963100198042520800002080000200392003911800211091010800001000103502000141604112007480000102004020040200402004020040
8002420039150000066004025800101080000108000050640000000200202003920039999631001980010208000020800002003920039118002110910108000010000035020007162672003680000102004020040200402004020040
800242003915000002880082258001010800001080000506400000152002020039200399996310019800102080000208000020039200391180021109101080000100010350205061604132003680000102004020040200402004020040
80024200391500000249002302580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000103502000101601152003680000102004020040200402004020040
800242003915000002850082258001010800001080000506400000052002020039200399996310019800102080000208000020039200391180021109101080000100000050205041605122003680000102004020040200402004020040
8002420039150000027900822580010108000010800005064000001520020200392003999963100198001020800002080000200392003911800211091010800001000103502054416012102003680000102004020040200402004020040
80024200391500000150082258001010800001080000506400000002002020039200399996310019800102080000208000020039200391180021109101080000100010350205011160952003680000102004020040200402004020040
80024200391500000234008225800101080000108000050640000015200202003920039999631001980010208000020800002003920039118002110910108000010000035020005160692003680000102004020040200402004020040
800242003915000002460061258001010800001080000506400000002002020039200399996310019800102080000208000020039200391180021109101080000100010350205010160552003680000102004020040200402004020040
80024200391500000255008225800101080000108000050640000015200202003920039999631001980010208000020800002003920039118002110910108000010000035020005160452003680000102004020040200402004020040