Apple M1 Microarchitecture Research by Dougall Johnson

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

FACGT (vector, 4H)

Test 1: uops

Code:

  facgt v0.4h, v0.4h, v1.4h
  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)03080b1e3f4e51inst 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)a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000001873116111787100020382038203820382038
10042037150001051687251000100010002646801201820372037157231895100010002000203720371110011000240073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203716000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371500186116872510001000100026468002018203720371572318951000100020002037203711100110000120073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720831110011000070073116111787100020382038203820382038
1004203715000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203715000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  facgt v0.4h, v0.4h, v1.4h
  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)031e3a3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200852003820038
102042003715001115196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000107101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000207101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000207101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010005637101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000207101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100100640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100106640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100100640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100206640216221978510000102003820038200382003820038
100242003715015661196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100103640216221978510000102003820038200382003820038
10024200371501261196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100003640216221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000100103640216221978510000102003820038200382003820038
1002420084151061196874410010121000010100005028489630200180200372003718444318767100102010000202000020037200371110021109101010000100102033663332321978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000100006640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  facgt v0.4h, v1.4h, v0.4h
  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)0309181e3f4e51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000084196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150000251196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150000145196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720181111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001211000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03070a191e1f3a3f4e51inst 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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150110002671968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000064410161051978510000102003820038200382003820038
10024200371501100026719687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000644101610101978510000102003820038200382003820038
10024200371501100026719687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000644101610101978510000102003820038200382003820038
100242003715011000216219687251004610100001010000722849227020018200372003718444318767100102010000202000020037200371110021109101010000101600644101610101978510000102003820038200382003820038
10024200371501111448826401967625100251010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000064451610101978510000102008520038200382003820038
10024200371501100026719687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000644101610101978510000102003820038200382003820038
100242003715011000267196872510010101000010100005028476800200182003720037184443187671001020100002020336200372003711100211091010100001000006441016881978510000102003820038200382003820038
1002420037150110002671968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010001064410165101978510000102003820038200382003820038
10024200371501100027321968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000064411161081978510000102003820038200382003820038
1002420037150110002671968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000064410161051978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  facgt v0.4h, v8.4h, v9.4h
  facgt v1.4h, v8.4h, v9.4h
  facgt v2.4h, v8.4h, v9.4h
  facgt v3.4h, v8.4h, v9.4h
  facgt v4.4h, v8.4h, v9.4h
  facgt v5.4h, v8.4h, v9.4h
  facgt v6.4h, v8.4h, v9.4h
  facgt v7.4h, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0308090b191e3f51inst 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)9fa0a1accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511021611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511031611200350800001002003920039200392003920039
802042003815700000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000511011611200350800001002003920039200392003920039
802042003815000000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100010511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a1e3f51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200471501039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020161611112003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020121612112003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020111612132003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020121612122003580000102003920039200882003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020111611122003580000102003920039200392003920039
800242003815000514258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020121612102003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020131613112003580000102003920039200392003920039
800242003815000186258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020121612132003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160194200382003811800211091010800001005020101611122003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001005020151612122003580000102003920039200392003920039