Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZU (scalar, integer, S to S)

Test 1: uops

Code:

  fcvtzu s0, s0
  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
1004303723012425472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303724061254725100010001000398160130183037303724143289510001000100030373037111001100049073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372506125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu s0, s0
  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)030f1e3a3f4e51inst 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)9fa6a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723203306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010007101161129633100001003003830038300383003830038
1020430037233041706129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000027101161129633100001003003830038300383003830038
10204300372330348061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000215007101161129633100001003003830038300383003830038
102043003723304806129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723204506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101162129633100001003003830038300383003830038
102043008023301506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037233022806129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037233044106129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723300072629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129697100001003003830038300383003830038
102043003723304206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300863003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b1e3f4e51inst 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)9fa0a1a6a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728291728767101612010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222970110000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373008428286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100100640216322962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu s0, s8
  fcvtzu s1, s8
  fcvtzu s2, s8
  fcvtzu s3, s8
  fcvtzu s4, s8
  fcvtzu s5, s8
  fcvtzu s6, s8
  fcvtzu s7, s8
  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)0304070a3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591550117225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511821611200360800001002004020040200402004020040
80204200391550117225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391550113025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391550113025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200860800001002004020092200922004020094
802042003915501130258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118116112003614800001002004020040200402004020040
80204200391600113025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391550113025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391550113025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391550113025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391550113025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e1f3a3f51inst 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)5f60696b6d6edispatch 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)9fa0a1a6a7a8a9acbccfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391560200000040258001010800001080000506400000020020020039200399996310019800102080000208000020039200391180021109101080000100000100050200001216332003680000102004020040200402004020040
80024200391550200000040258001010800001080000506400000020020020039200391002431001980620208000020800002003920039118002110910108000010203110325305143000592742032580000102034720344203482040220450
800242050615802089118870412537172806961080777108084950645650002034402039720407100703910231807342080823208083620402202409180021109101080000100000003051640005111332039580000102045320457204572045920454
8002420453159120591188792029731878088710807801080847506465120020336020444204011006137102598094920810522080945205502046281800211091010800001004000294305020020316332003680000102029820456202992040720456
80024204451570218210568802306280790108078110802095064162400202200204542024910024451012780322208020822802092003920039118002110910108000010000000065020000516342003680000102008920040200402004020040
80024200391610000000036225800101080000108000050640000002002002003920039999631001980010208000020800002009320039118002110910108000010000000005020000316372003680000102004020091200402004020040
8002420039161020000004025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000000005020000316472003680000102004020040200402004020040
8002420039161020000004025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000000005020000316332003680000102004020040200402004020040
8002420039155020000004025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000000005020000316332003680000102004020040200402004020040
8002420039155020000004025800101080000108000050640000002002002003920039999631001980010208000020800002003920039118002110910108000010000000005020000716332003680000102004020040200402004020040