Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZU (vector, integer, 4H)

Test 1: uops

Code:

  fcvtzu 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)03191e3f4e5051inst issue (52)~issue fp/simd (54)~issue ld/st (55)~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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037240043625473021251000100067481000398160030183037303724143289510001000100030373037111001100000073116112729100030383038303830383038
1004303724006125470251000100001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037250013125470251000100001000398160130183037303724143289510001000100030373037111001100001073116112629100030383038303830383038
1004303724006125470251000100001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061253802510001000010003981601301830373037241432895100010001000303730371110011000025073116112629100030383038303830383038
1004303723006125470251000100001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723006125470251000100001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724006125470251000100001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230044825470251000100001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724006125470251000100001000398160030183037303724143289510001000100030373037111001100000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu 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)0304081e3f4e51inst 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)9fa0acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233100612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007102162229633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300375110201100991001001000010000007102162229633100001003003830038300383003830038
10204300372330007542954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007102162229633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007102162229633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000007102162229633100001003003830038300383003830038
102043003723300013142954725101001001000011910000500428256813001830037300372826432874510100200100002001000030037300371110201100991001001000010000007102162229633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037301701110201100991001001000010000007102162229633100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007102162229633100001003003830038300383003830038
102043003723300010329547251010010010000100100005004277160030018300373003728264192874510100200100002001000030037300371110201100991001001000010000007102162229633100001003003830038300383003830038
1020430037233000892954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000007103162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037224000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000026402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018030037300372828603287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu v0.4h, v8.4h
  fcvtzu v1.4h, v8.4h
  fcvtzu v2.4h, v8.4h
  fcvtzu v3.4h, v8.4h
  fcvtzu v4.4h, v8.4h
  fcvtzu v5.4h, v8.4h
  fcvtzu v6.4h, v8.4h
  fcvtzu 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)030b1e1f3f51inst 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)9fa0a1a8a9acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059155000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039155000582580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039156030302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420039155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040
8020420112155000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151181620036800001002004020040200402004020040

1000 unrolls and 10 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)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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420059155040258001010800001080000506400001520020200392003999963100198001020800002080000200392003911800211091010800001000502050161612122003680000102004020040200402004020040
8002420039155065325800101080000108000050640000152002020039200399996310019800102080000208000020039200393180021109101080000101050205110168132003680000102004020040200402004020040
8002420039155040258001010800001080000506400001520020200392003999963100198001020804182080000200392003911800211091010800001000502050121612112003680000102004020040200402004020040
800242003915604025800101080000108000050640000052002020039200399996310019800102080000208000020039200391180021109101080000100050200071610122003680000102004020040200402004020040
8002420039155040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000502051101610122003680000102004020040200402004020040
8002420039156040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001010502051131610112003680000102004020040200402004020040
8002420039155040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000502000121610122003680000102004020040200402004020040
8002420039155040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000502050121611122003680000102004020040200402004020040
800242003915604025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100050205181612142003680000102004020040200402004020040
8002420039155040258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000502001141612122003680000102004020040200402004020040