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, fixed-point, 4S)

Test 1: uops

Code:

  fcvtzu v0.4s, v0.4s, #3
  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)031e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073316222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723001032547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723270612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723001242547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724001042547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu v0.4s, v0.4s, #3
  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)0318191e3a3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001002167101161129633100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001001267101161129633100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001003607101161129633100001003003830038300383003830038
1020430037232000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001002737101161129633100001003003830038300383003830038
102043003723300006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100097101161129633100001003003830038300383003830038
102043003723300006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100807101161129633100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001002907101161129633100001003003830038300383003830038
10204300372330000579295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001001697101161129633100001003003830038300383003830038
10204300372330000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010031127101161129633100001003003830038300383003830038
102043003723300006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100607101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3a3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216122962910000103003830038300383003830038
100243003722400006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010013640216222962910000103003830038300383003830038
1002430037225001206129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037224010019029538251001012100001210000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010010640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu v0.4s, v8.4s, #3
  fcvtzu v1.4s, v8.4s, #3
  fcvtzu v2.4s, v8.4s, #3
  fcvtzu v3.4s, v8.4s, #3
  fcvtzu v4.4s, v8.4s, #3
  fcvtzu v5.4s, v8.4s, #3
  fcvtzu v6.4s, v8.4s, #3
  fcvtzu v7.4s, v8.4s, #3
  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)033f51inst 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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049156302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001002011151181160020036800001002004020040200402004020040
8020420039155302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040202462004020040
8020420039155512580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039156302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155582580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020094
8020420039155302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039156302580108100800081008002050064013220020020039200399977699908012020080032200800322003920039118020110099100100800001000311151180160020036800001002004020040200402004020040

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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020216232003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020216332003680000102004020040200402009120040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316332003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020216332003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010305020316332003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010505020216232003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010105020316322003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010265020316332003680000102004020040200402004020040
8002420039155082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316332003680000102004020040200402004020040
8002420039156040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020216332003680000102004020040200402004020040