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, 2S)

Test 1: uops

Code:

  fcvtzu v0.2s, v0.2s
  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)60696b6d6edispatch 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
10043037230103254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724061254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230103254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724079254725100010001000398160030180303730372414328951000100010003037303711100110000373216222629100030383038303830383038
1004303723061254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372312105254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037231261254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723061254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723061254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303724061254725100010001000398160030180303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu v0.2s, v0.2s
  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)031e3a3f4e51inst 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)9fa0a1a8cfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233008929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372331206129547251010010010000100100005004277160130018300373003728271728741101002001000820010008300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372330025129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003007130038300383003830038
1020430037232008929547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
10204300372321206129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710021611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038
1020430037233006129547251010010010005100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000710011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3a3f4e51inst 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)9fa0a1a6a8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000000462829493134100711210056141105093428632213023430368304162830725288791091224111502210652304183041781100211091010100001022211950385103974629919210000103051230512304663050930513
100243022323611061452880061295472510010101000010100006042771601300903050830554283265028804100102010000201000030037300371110021109101010000100000064003162229629010000103003830038300383003830038
100243003723300018008229547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
10024300372410000006129547251001010100001010000504277160130018300713003728286328767100102010000201000030037300371110021109101010000100000064042162229629010000103003830038300383003830038
100243003724100045006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
10024300372330000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000364002162229629010000103003830038300383003830038
100243003723200000023029547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038
10024300372250000004962954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000012664002162229629010000103003830038300383003830038
10024300372240000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000064002162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu v0.2s, v8.2s
  fcvtzu v1.2s, v8.2s
  fcvtzu v2.2s, v8.2s
  fcvtzu v3.2s, v8.2s
  fcvtzu v4.2s, v8.2s
  fcvtzu v5.2s, v8.2s
  fcvtzu v6.2s, v8.2s
  fcvtzu v7.2s, v8.2s
  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)03090b1e1f3f51inst 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)9fa0a1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039155004203025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
8020420039156006303025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
8020420039155003903025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
802042003915510607925801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
802042003916100007925802121008000810080020500640132120020200392003999776999080120200803482008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
80204200391550024050525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
8020420039155000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036211800001002004020040200402004020040
802042003915500003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
80204200391550027017125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040
8020420039156003603025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000001115118016002003600800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070818191e1f3f4d4f51inst 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)5f6061696d6edispatch 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)9fa0a1a6a7a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511550000120367002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502007165320036080000102004020040200402004020040
800242003915500000040002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502004163520036080000102004020040200402004020040
800242003915500000040002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502004165520036080000102004020040200402004020040
800242003915600000082002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502005165520036080000102004020040200402004020040
800242003915500000040002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502005164620036080000102004020040200402004020040
800242003915500000054002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502006165520036080000102004020040200402004020040
800242003924800000040002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502003164620036080000102004020040200402004020040
800242003915500000061002580010108000010800005064000001020020200392003999963100198001020800002080000200392003911800211091010800001000000000502005165520036080000102004020040200402004020040
800242003915500000040002580010108000010800005064000011020020200392003999963100198001020800002080000200392003911800211091010800001000000000502005166420036080000102004020040200402004020040
800242003915500000082002580010108000010800005064000000020020200392003999963100198001020800002080000200392003911800211091010800001000000000502003165520036080000102004020040200402004020040