Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMU (vector, 4H)

Test 1: uops

Code:

  fcvtmu v0.4h, v0.4h
  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)a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037231261254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289511481000100030373037111001100000073116112629100030383038303830383038
1004303723084254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724084254725100010001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
10043037240179254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724084254725100010001000398160130183037303724143289510001000100030373037111001100000373116112629100030383038303830383038
1004303723061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtmu v0.4h, v0.4h
  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)03081e3a3f4e51inst 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)9fa0a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007103161129633100001003003830038300383003830038
10204300372330006312954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037234000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372330005362954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000600612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
1002430037225000004132954725100101010000101000050427716000300543003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
1002430037225000210612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
1002430037225000360612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716010300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
100243003722500000612954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038
1002430037225000002292954725100101010000101000050427716000300183003730037282863287671001020100002010000300373003711100211091010100001000064000216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtmu v0.4h, v8.4h
  fcvtmu v1.4h, v8.4h
  fcvtmu v2.4h, v8.4h
  fcvtmu v3.4h, v8.4h
  fcvtmu v4.4h, v8.4h
  fcvtmu v5.4h, v8.4h
  fcvtmu v6.4h, v8.4h
  fcvtmu v7.4h, v8.4h
  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)03080b1e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039156000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182163320036800001002004020040200402004020040
8020420039155000302580108100800881008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184163420036800001002004020040200402004020040
80204200391550001422580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184163420036800001002004020040200402004020040
8020420039156000512580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010003011151183164420036800001002004020040200402004020040
8020420039155110302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184164320036800001002004020040200402004020040
802042003915600129012580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163320036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182162220036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163320036800001002004020040200402004020040
8020420039155001240225801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100420011151184162320036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183167320036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a1e3f51inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd0icache miss (d3)d5d6d9dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501551001082258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211090101080000100050200021600222003680000102004020040200402004020040
80024200391560000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211090101080000100050203121621332003680000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211090101080000100050200021600222003680000102004020040200402004020040
80024200391550110040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211090101080000100050200021600422003680000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211090101080000100050200031600442003680000102004020040200402004020040
800242003915500000705258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211090101080000100050200031600222003680000102004020040200402004020040
80024200391550000040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211090101080000100050200031600222003680000102004020040200402004020040
80024200391610000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211090101080000100050200021600322003680000102004020040200402004020040
80024200391550000040258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211090101080000100050200021600422003680000102004020040200402004020040
80024200391550000082258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211090101080000100050200021600232003680000102004020040200402004020040