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, 2D)

Test 1: uops

Code:

  frintx v0.2d, v0.2d
  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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723087254725100010001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037220145254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
10043037232761254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintx v0.2d, v0.2d
  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)030818191e1f3f4e51inst 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)9fa1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001000071011611296330100001003003830038300383003830038
102043003722500012072629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373008511102011009910010010000100001030071011611296330100001003003830038300383003830038
102043003722500012886129547251010010010000100100005004277160130018300373003728264328745101002001016420010000300373003711102011009910010010000100000030071011611296330100001003003830038300383003830038
102043003722500012010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100001032171011611296330100001003003830038300383003830038
102043003722500024010329547251010010010000100100005004277160130090300373003728264328745101002001000020010000300373003711102011009910010010000100000030071011611296330100001003003830038300853003830038
10204300372250001206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001000071011611296330100001003003830038300383003830038
10204300372250001206129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100001000071011611296330100001003003830038300383003830038
102043003722400012010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
10204300372250003010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100401030071011611296330100001003003830038300383003830038
102043003722500012029329547251010010010000100100005004277160030054300373003728264328745101002001000020010000300373003711102011009910010010000100000030071011611296330100001003003830038300383003830038

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)6061696d6edispatch 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)9fa0a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722512103295472510010101000010100005042771601430018300373003728286328767100102010000201000030037300371110021109101010000100036404216222962910000103003830038300383003830038
100243003722512103295472510010101000010100005042771601430018300373003728286328767100102010000201000030037300371110021109101010000100136404216222962910000103003830038300383003830038
100243003722512103295472510010101000010100005042771601330018300373003728286328767100102010000201000030037300371110021109101010000100106403216222962910000103003830038300383003830038
100243003722512103295472510010101000010100005042771601230018300373003728286328767100102010000201000030085300371110021109101010000100066402216222962910000103003830038300383003830038
10024300372240103295472510010101000010100005042771601230018300373003728286328767100102010000201000030037300371110021109101010000100036402216222962910000103003830038300383003830038
100243003722412103295472510010101000010100005042771601230018300373003728286328767100102010000201000030037300371110021109101010000100136402216222962910000103003830038300383003830038
100243003722512103295472510010101000010100005042771601230018300373003728286328767100102010000201000030037300371110021109101010000100036402216222962910000103007930038300383003830038
100243003722512103295472510010101000010100005042771601230018300373003728286328767100102010000201000030037300371110021109101010000100136402216222962910000103003830038300383003830038
100243003722512103295472510010101000010100005042771601230018300373003728286328767100102010000201000030037300371110021109101010000100006402216222962910000103003830038300383003830038
10024300372251261295472510010101000010100005042771601230018300373003728286328767100102010000201000030037300371110021109101010000102136402216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintx v0.2d, v8.2d
  frintx v1.2d, v8.2d
  frintx v2.2d, v8.2d
  frintx v3.2d, v8.2d
  frintx v4.2d, v8.2d
  frintx v5.2d, v8.2d
  frintx v6.2d, v8.2d
  frintx v7.2d, v8.2d
  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)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)9fa0a8acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915012722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000100111511816020036800001002004020040200402004020040
80204200391500722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040
802042003915004522580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000100111511816020036800001002004020040200402004020040
802042003915012722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000100111511816020036800001002004020040200402004020040
80204200391500722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000100111511816020036800001002004020040200402004020040
80204200391500722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000130111511816020036800001002004020040200402004020040
802042003915012722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000130111511816020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010001180111511816020036800001002004020040200402004020040
802042003915012302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000111511816020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040a191e3f51inst 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)9fa0a8a9accfd2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401501002763258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000251619242003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000271628282003680000102004020040200402004020040
80024200391500001240258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000281628282003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000281628282003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000281628282003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002005820039200399996310019800102080000208000020039200391180021109101080000100000502000141625152003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000281628282003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000151628152003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000281615272003680000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100000502000141628142003680000102004020040200402004020040