Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZS (vector, integer, 2D)

Test 1: uops

Code:

  fcvtzs v0.2d, v0.2d
  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)03191e3f4e51inst 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
100430372400103254725100010001000398160030180303730372414328951000100010003037303711100110006073116112629100030383038303830383038
10043037240061254725100010001000398160030180303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230071254725100010001000398160030180303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037240061254725100010001000398160030180303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240061254725100010001000398160030180303730372414328951000104310003037303711100110002073116112629100030383038303830383038
10043037240061254725100010001043398160030180303730372414328951000100010003037303711100110001373116112629100030383038303830383038
10043037230061254725100010001000398160030180303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372301261254725100010001000398160030180303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037240061254725100010001000398160130180303730372414328951000100010003037303711100110000073116112700100030383038303830383038
10043037230061254725100010001000398160030180303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs v0.2d, v0.2d
  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)03070a1e3f4e51inst 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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300121242954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372320004052954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372320001312954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010020000071021622296330100001003003830038300383003830038
102043003723300094829547251010010010000100100005004277160030018300373003728264328745101242001017920010008300373003711102011009910010010000100002111171711611296490100001003003830038300383003830038
1020430037232110612954725101001001000010010000500427716003001830037300372827162874010100200100082001000830037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
1020430037233000822954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372330001242954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372330004602954725101001001000010010000500427716003006430037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038
10204300372330002322954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037232006129547251001010100001010000504277160130018030085301322828632876710010201000020100003003730037111002110910101000010000682216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001012100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216212962910000103003830038300383003830038
1002430037233006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs v0.2d, v8.2d
  fcvtzs v1.2d, v8.2d
  fcvtzs v2.2d, v8.2d
  fcvtzs v3.2d, v8.2d
  fcvtzs v4.2d, v8.2d
  fcvtzs v5.2d, v8.2d
  fcvtzs v6.2d, v8.2d
  fcvtzs v7.2d, v8.2d
  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)03080a0b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039156000000056025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000000111511811612200360800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000000111511821612200360800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000000111511811622200360800001002004020040200402004020040
802042003915600000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000000111511821631200360800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010040000000111511821602200360800001002004020040200402004020040
8020420039156000000033025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000000111511821632200360800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000000111511831612200360800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039204021180201100991001008000010000010000111523942821203290800001002039720445204122039920397
8020420454158010869336162036818079810080697102808525116459100203852040520454100492310203809372028054820280972204532045191802011009910010080000100022010353841115185411535203252800001002046020470204552046620463
802042045815911028114970435351758089110380794100809505006467241203872046020454100144210205810442048085320280955201482049810180201100991001008000010000001000111511821622200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3a3f51inst 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)5f696d6edispatch 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)9fa8acc5cdcfd0icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500031725800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020003160005520036080000102004020040200402004020040
80024200391550306325800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000005020003160005520036080000102004020040200402004020040
800242003915501204025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020003160003320036080000102004020040200402004020040
800242003915600012225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020005160005420036080000102004020040200402004020040
80024200391560008425800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020003160004420036080000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001003005020003160007720036080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020003160002420036080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020004160004420036080000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020004160004420036080000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020003160003420036080000102004020040200402004020040