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, 2S)

Test 1: uops

Code:

  fcvtzs 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)03191e1f3f4e51inst 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)a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372406061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372500061254725100010001000398160030183037303724143289510001000100030373037111001100003073116112629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372506061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372400061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303724015061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372400089254725100010001000398160030183085318124143289510001000100030373037111001100000073116112629100030383038303830383038
100430372500061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs 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)030918191e1f3f4e51inst 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)696d6edispatch stall (70)72scheduler 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)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021622296332100001003003830038300383003830038
102043003722400000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021632296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000171021622296330100001003003830038300383003830038
102043003722400000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716030018300373003728264032874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160300183003730037282640262874510100200100002001000030037300371110201100991001001000010000071021622296330100001003003830038300383003830038

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)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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500072629547421001810100241010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010001080640216222962910000103003830038300383003830038
100243003722500061295472510010101000010100005042771600300183300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722400025129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010001770640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010001470640216222962910000103003830038300713003830038
1002430037225000612954725100101010000101000050427716013001803003730037282863287671001020100002010000300373003711100211091010100001000120640216222962910000103003830038300383003830038
10024300372240006312954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000990640216222962910000103003830038300383003830038
100243003722400072629547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010001200640216222962910000103003830038300383003830038
10024300372240006129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010001200640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010001380640216222962910000103003830038300383003830038
10024300372250006129547251001010100001010000504277160030018030037300372828632876710010201000020100003003730037111002110910101000010001260640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzs v0.2s, v8.2s
  fcvtzs v1.2s, v8.2s
  fcvtzs v2.2s, v8.2s
  fcvtzs v3.2s, v8.2s
  fcvtzs v4.2s, v8.2s
  fcvtzs v5.2s, v8.2s
  fcvtzs v6.2s, v8.2s
  fcvtzs 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)0308090b18191e1f3f51inst 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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391550000012010025801081008000810080020500640132020020200392003999776999080120200800322008003220039201921180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080438200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020139200402004020040
802042003916100000004425801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000200011151180160020036800001002004020040200402004020040
8020420039156000301203025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000611151180160020036800001002004020040200402024820040
802042003915500000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000010311151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039155000000022025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915500000003025801081008000810080020500640132120020200392003999776999080534200800322008003220039200391180201100991001008000010000000311151180160020036800001002014220040200402004020040
8020420039155000000014225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3f51inst 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)9fa6a8accficache miss (d3)itlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511551004025800101080000108000050640000020020200392003999963100198001020800002080000200392003921800211091010800001020475502001916572003680000102004020040200402004020040
800242003915500082258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000502001716892003680000102004020040200402004020040
800242003916000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000502001516572003680000102004020040200402004020040
800242003915501204025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050200210161192003680000102004020040200402004020040
800242003915500040258001010800001080000506400001200202003920039999631001980010208000020800002003920092118002110910108000010000502002716572003680000102004020040200402004020040
800242003915500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000502002916562003680000102004020040200402004020040
8002420039155000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020021116782003680000102004020040200402004020040
800242003915500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000502001416482003680000102004020040200402004020040
8002420039155000135258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000502001516882003680000102004020040200402004020040
8002420039156000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020015167102003680000102004020040200402004020040