Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGT (scalar, zero, D)

Test 1: uops

Code:

  fcmgt d0, d0, #0
  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)03041e3f4e51inst 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
1004203715106116862510001000100026452102018203720371571318951000100010002037203711100110000073216111792100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715008216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716008216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715008216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt d0, d0, #0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b181e1f3f4e51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500003606119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100000111718016019801100001002003820038200382003820038
10204200371500002106119686251010010010000100100005002847521120018200372003718428718741101002001000820010008200372003711102011009910010010000100000111717016019800100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100000111718017019800100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100000111718016019800100001002003820038200382003820038
10204200371500000012419686251010010010000100100005002847521120018200372003718428618740101002001000820410008200372003711102011009910010010000100000111717016019801100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100000111717016019800100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718428718741101002001000820010008200372003711102011009910010010000100000111718016019800100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718428718741101002001000820010008200372003711102011009910010010000100000111717016019800100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718428718740101002001000820010008200372003711102011009910010010000100000111718016019800100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521120018200372003718428718741101002001000820010008200372003711102011009910010010000100000111717016019801100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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)9fa7a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715006119686251001010100001010000502848785120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715008219686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371502136119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmgt d0, d8, #0
  fcmgt d1, d8, #0
  fcmgt d2, d8, #0
  fcmgt d3, d8, #0
  fcmgt d4, d8, #0
  fcmgt d5, d8, #0
  fcmgt d6, d8, #0
  fcmgt d7, d8, #0
  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)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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511811600200350800001002003920039200392003920039
80204200381502129258010810080008100800205006401321200772003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038998769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200850800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801601200350800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 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)5f60696d6edispatch 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150039392580010108000010800005064000041200192003820038999631001880010208000020800002003820038118002110910108000010000000502017161782003580000102003920039200392003920039
80024200381500039258001010800001080000506400007120019200382003899963100188001020800002080000200382003811800211091010800001000000050208161782003580000102003920091200882003920039
800242003815030392580010108000010800005064000071200192003820038999631001880010208000020800002003820038118002110910108000010200000502017161772003580000102003920039200392003920039
800242003815000392580010108000010800005064000081200192003820038999631001880010208000020800002003820038118002110910108000010000000502071617172003580000102003920039200392003920039
800242003815000392580010108000010800005064000071200192003820038100103100188001020800002080000200382003811800211091010800001000000050208161762003580000102003920039200392003920039
80024200381500039258001010800001080000506400007120019200382003899963100188001020800002080000200382003811800211091010800001000000050208168172003580000102003920039200392003920039
800242003815000392580010108000010800005064000071200192003820038999631001880010208000020800002003820038118002110910108000010000000502061617172003580000102003920039200392003920039
80024200381500243925800101080000108000050640000712001920038200389996310018800102080000208000020038200381180021109101080000100000005020171617172003580000102003920039200392003920039
8002420038150003925800101080000108000050640000812001920038200389996310018800102080000208000020038200381180021109101080000100000005020171617172003580000102003920039200392003920039
8002420038150003925800101080000108000050640000712001920038200389996310018800102080000208000020038200381180021109101080000100000005020171616162003580000102003920039200392003920039