Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (register, 8H)

Test 1: uops

Code:

  cmeq v0.8h, v0.8h, v1.8h
  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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073416111787100020382038203820382038
1004203715726116872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382086203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371508216872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116221787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371508216872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116221787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq v0.8h, v0.8h, v1.8h
  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)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)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007102161119791100001002003820038200382003820038
10204200371500661968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715001241968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010003007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371490611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715001701968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080918191e3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785210000102003820038200382003820038
10024200371500000025119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715000000114619687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037155000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006403162219785010000102003820038200382003820038
1002420037150000008219687251001010100001010000502847680120065200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
10024200371500000093919687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100036402162219785010000102003820038200382003820038
1002420037150100006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmeq v0.8h, v1.8h, v0.8h
  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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002042033020037200371110201100991001001000010000071011611197910100001002003820085200382003820038
1020420037150010101968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010010071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842291874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

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)696d6edispatch 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640416331978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371490103196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500536196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331978510000102003820038200382003820038
10024200371500149196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000640316331982310000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmeq v0.8h, v8.8h, v9.8h
  cmeq v1.8h, v8.8h, v9.8h
  cmeq v2.8h, v8.8h, v9.8h
  cmeq v3.8h, v8.8h, v9.8h
  cmeq v4.8h, v8.8h, v9.8h
  cmeq v5.8h, v8.8h, v9.8h
  cmeq v6.8h, v8.8h, v9.8h
  cmeq v7.8h, v8.8h, v9.8h
  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)03071e3f51inst 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)696d6edispatch 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)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150197325801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511021622200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511021611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011721200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
80204200381500040258010010080000100800005006400002001920038200389973399968010020080000200160000200382003811802011009910010080000100000005112316122003525800001002003920039200392003920039
8020420038150004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150003925801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e1f3f51inst 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)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)9fa0a1a6a7a8a9acc2c5cfd0d5d6d9dadbddinst fetch restart (de)dfe0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815000000003925800101080000108000050640000102001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243516000573200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243716000753200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243716000753200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243516211773200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243516000753200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243716000753200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996731001880010208000020160000200382003811800211091010800001000000000050243716000753200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243716000773200350080000102003920039200392003920039
8002420038150000001503925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243716000573200350080000102003920039200392003920039
800242003815000000003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000000000050243516000573200350080000102003920039200392003920039