Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPU (vector, 2D)

Test 1: uops

Code:

  fcvtpu 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)03191e1f3f4e51inst 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
1004303724000103254725100010001000398160130183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303724024061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372410061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
1004303723012061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372303061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtpu 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)030e0f18191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0e2? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233001112131295474410100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001003071011611296330100001003003830038300383003830038
10204300372418000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730082111020110099100100100001000071011611296330100001003003830038300383003830038
102043003723200001261295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003723300001266295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003723300001261295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000080611611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000071031611296330100001003003830038300383003830038
1020430037233000002512954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010001271011611296330100001003003830038300383003830038
102043003723300000103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183007030037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828603287671001020100002010172300373003711100211091010100001023640216222962910000103003830038300383003830038
10024300372331214529547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383008130038
100243003722506129547251001010100001010000504277160130018030037300372828603287671001020100002010000300373003711100211091010100001000640216222970110000103003830038300383003830038
100243003722506129547251001010100001010000504278512030018030037300372828603287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
100243003722506129547431001010100001010000504277160130018030037300372828603287671001020100002010000300373003711100211091010100001000669216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtpu v0.2d, v8.2d
  fcvtpu v1.2d, v8.2d
  fcvtpu v2.2d, v8.2d
  fcvtpu v3.2d, v8.2d
  fcvtpu v4.2d, v8.2d
  fcvtpu v5.2d, v8.2d
  fcvtpu v6.2d, v8.2d
  fcvtpu 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)030b18191e1f3f51inst 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)5e60696d6edispatch 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)9fa1a8acc2c3c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420050155000210114258010810080008100800205006401320120020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
802042003915510012030258010810080008100800205006401320120020200392003999776999080120200800322008003220039200391180201100991001008000010001000111511801600200860800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
80204200391560000072258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000000111511801600200360800001002004020040200402004020040
802042003916000012030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200391180201100991001008000010000300111511801600200360800001002004020040200402004020040
80204200391550000030258010810080008100800205006401320020020200392003999776999080120200800322008003220039200891180201100991001008000010000000111511801600200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3a3f51inst 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)9fa0a6a8a9acc2c3cdcfd0d2d5d6dadbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051156000465004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000050370041600772003680000102004020040200402004020040
8002420039155000486004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000050200041600432003680000102004020091200402004020040
8002420039155000105004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100010000050200041600342003680000102004020040200402004020040
800242003915500000015625800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050200041600672003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000050200031600662003680000102004020040200402004020040
800242003915500060004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000050200031600342003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000050200071600442003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000050200071600432003680000102004020040200402004020040
800242003915500036004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000050200031600442003680000102004020040200402004020040
80024200391550000004025800101080000108000050640000102002020090200399996310019800102080000208000020039200391180021109101080000100000000050200071600662003680000102004020040200402004020040