Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTNU (scalar, S to S)

Test 1: uops

Code:

  fcvtnu 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)696d6edispatch 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
10043037230145254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
10043037240145254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303724084254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtnu 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)031e3f4e51inst 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
102043003722593101329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129538251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722508229547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003721102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225156129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722466129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010001237101161129633100001003003830038300383003830038
1020430037225366129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308191e1f3f4e51inst 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)9fa6a8acc5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372330000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
10024300372330000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
10024300372250030612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001803003730037282863287671001020100002010000302263003711100211091010100001000006400216222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716013001803003730037282863287671001020100002010000300373003711100211091010100001000006400316222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000006404216222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001803003730037282863287671001020100002010653300373003711100211091010100001000006400216222962910000103003830038300383003830038
10024300372250000612954725100101010000101000050427716003001803003730037282863287671001020100002010000300373003711100211091010100001000006400216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtnu s0, s8
  fcvtnu s1, s8
  fcvtnu s2, s8
  fcvtnu s3, s8
  fcvtnu s4, s8
  fcvtnu s5, s8
  fcvtnu s6, s8
  fcvtnu 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)031e3f51inst 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)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)9fa1a8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115503025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118116020036800001002004020040200402004020040
8020420039155011725801081008000810080108500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016120036800001002004020040200402004020040
8020420039155030258010810080008100800205006401321200202003920039997706999080120200800322008003220039200391180201100991001008000010000181115118016020036800001002004020040200402004020040
802042003915505825801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915603025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915507225801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e3a3f51inst 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)6061696d6edispatch 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)9fa0a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915600000402580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010000005020539166112003680000102004020040200402004020040
80024200391550000040258001010800001080000506400001520020200392003999963100198001020800002080000200392003911800211091010800001000000502053516542003680000102004020040200402004020040
800242003915500000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000005020537166112003680000102004020088200402004020040
800242003915500000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000005020004166112003680000102004020040200402004020040
800242003915600000402580010108000010800005064000005200202003920039999631001980010208000020800002003920039118002110910108000010010005020506165112003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000050200011161162003680000102004020040200402004020040
8002420039155000005152580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000005020541116452003680000102004020040200402004020040
80024200391610000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001004000502050716652003680000102004020040200402004020040
80024200391550000082258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000000502054616642003680000102004020040200402004020040
800242003915500000105258001010800001080000506400001520020200392003999963100198001020800002080000200392003911800211091010800001000000502054616532003680000102004020040200402004020040