Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTAU (vector, 4S)

Test 1: uops

Code:

  fcvtau v0.4s, v0.4s
  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
1004303724010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723010325472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtau v0.4s, v0.4s
  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)03081e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330030529547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372350126129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100037101161129633100001003003830038300383003830038
1020430037233008929547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233039729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372330053629547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038
10204300372330339429547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100037101161129633100001003003830038300383003830038
10204300372320010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030a1e3f4e51inst 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)9facc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250306129547251001010100001010000504277160030018300373003728286328767100102010000201048530084300371110021109101010000100000640316332962910000103003830038300383003830038
10024300372320016029547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037224006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103008530038300383003830038
1002430037224006129547251001010100001210000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037225006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtau v0.4s, v8.4s
  fcvtau v1.4s, v8.4s
  fcvtau v2.4s, v8.4s
  fcvtau v3.4s, v8.4s
  fcvtau v4.4s, v8.4s
  fcvtau v5.4s, v8.4s
  fcvtau v6.4s, v8.4s
  fcvtau v7.4s, v8.4s
  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)030b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing ld/st (5a)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)9fa0a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915600000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118116002003600800001002004020040200402004020040
802042003915600000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
802042003916100000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
802042003915600000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
802042003915500000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
8020420039155000120302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
802042003915500000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
802042003915500000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
8020420039155000008662580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040
802042003915500000302580108100800081008002050006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118016002003600800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd5d6dbddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501560000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502071616520036080000102004020040200402004020040
80025200391550000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502031606520036080000102004020040200402004020040
80024200391550000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502061605320036080000102004020040200402004020040
80024200391550000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502061605520036080000102004020040200402004020040
80024200391550000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100001000502051606620036080000102004020040200402004020040
80024200391550000000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502051603520036080000102004020040200402004020040
80024200391550000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502051606520036080000102004020040200402004020040
80024200391550000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502031605420036080000102004020040200402004020040
80024200391560000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502051605620036080000102004020040200402004020040
80024200391550000000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502061604620036080000102004020040200402004020040