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, fixed-point, 4S)

Test 1: uops

Code:

  fcvtzs 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)031e3f4e51inst 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
10043037231266125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037242706125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037231776125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816003018303730372414628951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs 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)030708090a0b18191e1f3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000000000346295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633000100001003003830038300383003830038
1020430037233000000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011651301083800100001003060230658307093070530657
10204307062464013113131716105688792942829210277163101121681195083442960880300183003730085283156429011121162281000020012151306603055915110201100991001001000010000023907007101161129633000100001003003830038300383003830038
102043003723300000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633000100001003003830038300383003830038
102043003723300000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633000100001003003830038300383003830038
102043003724400000003061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633000100001003003830038300383003830038
102043003723300000000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633000100001003003830038300383003830038
1020430037233000000000642295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129699000100001003003830038300383003830038
102043003723200000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000307101161129633000100001003003830038300383003830038
1020430037233000000000536295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633000100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b181e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000156612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037211002110910101000010000640214752229629010000103003830038300383003830038
1002430037241000010329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723300006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037233000396129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003723300006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722400036129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372250001986129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100306402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs v0.4s, v8.4s, #3
  fcvtzs v1.4s, v8.4s, #3
  fcvtzs v2.4s, v8.4s, #3
  fcvtzs v3.4s, v8.4s, #3
  fcvtzs v4.4s, v8.4s, #3
  fcvtzs v5.4s, v8.4s, #3
  fcvtzs v6.4s, v8.4s, #3
  fcvtzs 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)03181e3f51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200671550123025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391550123025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000003011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039155003025801081008000810080020500640132020020200902009099776100148012020080142200800322003920039118020110099100100800001000021481011151180160020036800001002004020040200402004020040
8020420039155003025803061008000810080020500640132120020200392009399776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039156003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039156093025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000010011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e243a3f51inst 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)9fa1a6a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051161000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100014850200616562003680000102004020040200402004020040
800242003915600040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200616462003680000102004020040200402004020040
800242003915500061258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200716782003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200416472003680000102004020040200402004020040
800242003915600040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200516562003680000102004020040200402004020040
800242003915500083258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010001050200816662003680000102004020040200402004020040
800242003915600040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200416642003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200416482003680000102004020040200402004020040
800242003915500061258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000350200516752003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050200516462003680000102004020040200402004020040