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, 8H)

Test 1: uops

Code:

  fcvtzu v0.8h, v0.8h
  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)03071e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037240126125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000373216222629100030383038303830383038
10043037240666125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004308523006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230126125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724006125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu v0.8h, v0.8h
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)ebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100137101161129633000100001003003830038300383003830038
1020430037233012629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038
1020430037232034029547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038
1020430037233074529547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038
1020430037233083929547251010010010000100100005004277160130018300373003728264328745101002001000020010182300373003711102011009910010010000100037101161129633000100001003003830038300383003830038
10204300372330161629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038
1020430037233036729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038
1020430037233043629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038
1020430037233016829547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038
102043003723312102829547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633000100001003003830038300383003830038

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)696b6d6edispatch 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225067295472510010101000010100005042771603001803003730037282860328767100102010000201000030037300371110021109101010000100006401116332962910000103003830038300383003830038
1002430037225096529547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722506729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722506729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010200640316332962910000103003830038300383003830038
100243003722506729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722506729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722506729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722506729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722506729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722406729547251001010100001010000504277160300180300373003728286032876710010201000020100003003730037111002110910101000010000640316442962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu v0.8h, v8.8h
  fcvtzu v1.8h, v8.8h
  fcvtzu v2.8h, v8.8h
  fcvtzu v3.8h, v8.8h
  fcvtzu v4.8h, v8.8h
  fcvtzu v5.8h, v8.8h
  fcvtzu v6.8h, v8.8h
  fcvtzu v7.8h, v8.8h
  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)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)9fa0a1a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006815500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151182163320036800001002004020040200402004020040
802042003915500000582580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151183163420036800001002004020040200402004020040
8020420039155000001182580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151183163320036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151183164320036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000211151183164520036800001002004020040200402004020040
8020420039155000001392580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151183163420036800001002004020040200402004020040
802042003915500000722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151183164420036800001002004020040200402004020040
8020420039155000001562580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151183164420036800001002004020040200402004020040
802042003916100000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151184162420036800001002004020040200402004020040
802042003915600012024225801081008000810080020500640132120020200392003999771299908012020080032200800322003920039118020110099100100800001000000011151184165420036800001002004020040200402004020040

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)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)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8acc2cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201616011122003680000102004020040200402004020040
8002420039156124452580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010010050201416013112003680000102004020040200402004020040
80024200391550402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201316012112003680000102004020040200402004020040
80024200391560402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201416013122003680000102004020040200402004020040
8002420039155040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020101606112003680000102004020040200402004020040
80024200391550402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010010050201116013112003680000102004020040200402004020040
8002420039155068258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000005020131607122003680000102004020040200402004020040
80024200391550402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201116013112003680000102004020040200402004020040
800242003915501242580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000050201216012112003680000102004020040200402004020040
80024200391560166258001010800001080000506400000120020200392003999963100198001020800002080000200392003911800211091010800001000005020121601292003680000102004020040200402004020040