Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGE (register, 4H)

Test 1: uops

Code:

  cmge 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)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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715011816872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715031316872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371508216872510001000100026468012018203720371572318951000110720002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge 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)030b18191e1f3a3f4e51inst 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)9facc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720179111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003714900000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150000000338196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002008520037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715000000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715000000082196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150000000578196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150000000124196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371501014719687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221984110000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500051919687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500216119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500021419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmge 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)03181e3f4e51inst 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)9fa0cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715010611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003714900611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150001211968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100208100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000010806119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000000053619687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000011406119687251001010100001010000502847680020018200372003718444031876710010201000020200002007020037111002110910101000010000000306402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444031876710010201033420200002003720037111002110910101000010020000006402162219785010000102003820038200382003820038
100242008415000000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003714900000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000022206119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
1002420037150000004206119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000040506119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018200372003718444031876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmge v0.4h, v8.4h, v9.4h
  cmge v1.4h, v8.4h, v9.4h
  cmge v2.4h, v8.4h, v9.4h
  cmge v3.4h, v8.4h, v9.4h
  cmge v4.4h, v8.4h, v9.4h
  cmge v5.4h, v8.4h, v9.4h
  cmge v6.4h, v8.4h, v9.4h
  cmge 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)0318191e3f51inst 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150009402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511031622200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000002001920239200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815000040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000004700511021622200350800001002003920039200392003920039
80204200381500030402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
8020420038150000632580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511031622200350800001002003920039200392003920039
80204200381500002322580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
8020420038150000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511021622200350800001002003920039200392003920039
802042003815011132402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100000000511032722200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150100000039258001010800001380000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000000051333300231600026132003500080000102003920039200392003920039
80024200381501010000392580010108000010800005064000002001920038200381002031001880010208000020160000202932003811800211091010800001000000000050200000281600016272003500080000102003920039200392003920039
8002420291150100000039258001010800001080000506415200200192003820038999631001880010208048720160000200382003811800211091010800001000000000050200000201600026262003500080000102003920039200392003920039
800242003815000000001762580010108000010800005064000002001920038200381000431001880010208019620160000200382003811800211091010800001000001214180050200000151600027212003500080000102003920039200392003920039
8002420038150000000039258001010800001080000506400001200192003820038999631001880010208009920160000200382003811800211091010800001000000000050200000221600027242003500080000102003920039200392003920039
80024200881510000000391628001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001002000000050233000257511019252003500080000102023920039200392003920039
80024200381500003210039258001010800001080000506400000200192003820038999631001880010208000020160000200882018911800211091010800001000001000050200000211900022282003500080000102003920039200392003920039
8002420291150000000045258001010800001080000506446081200192028520038999631001880010208000020160000200382003811800211091010800001000000000050233310242911128222003500080000102003920039200392003920039
800242003815000000001252580010108000010800005064000012001920038200389996281001880010208000020160000200382003811800211091010800001000000000050200000281800027182015300080000102003920039200392003920039
80024200381500030000123258001010800001080000506400001200192003820038999631001880010208000020160000200382003841800211091010800001000001000050223000261800027272003500080000102003920039200392003920039