Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (zero, 16B)

Test 1: uops

Code:

  cmeq v0.16b, v0.16b, #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)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)a0a6a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371706116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371566116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715216116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371506116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq v0.16b, v0.16b, #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)03080b1e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200106642003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715010061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000214100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03071e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100640416661978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000221000020037200841110021109101010000100640516661978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100640516651978610000102003820038200382003820038
100242003715009611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100640516451978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100640516561978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100640616661978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201016920037200371110021109101010000100640516661978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100640516551978610000102003820038200382003820038
100242003715000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100640516551978610000102003820038200382003820038
100242003715000611968625100101010000101000050284788720018200372003718443318767100102010000201000020037200371110021109101010000100640516641978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmeq v0.16b, v8.16b, #0
  cmeq v1.16b, v8.16b, #0
  cmeq v2.16b, v8.16b, #0
  cmeq v3.16b, v8.16b, #0
  cmeq v4.16b, v8.16b, #0
  cmeq v5.16b, v8.16b, #0
  cmeq v6.16b, v8.16b, #0
  cmeq v7.16b, v8.16b, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03070a1e3f51inst 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)9fa6a7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150110292580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013202001902003820038998869989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151371161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161220035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013202001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212003902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039
8020420038150110292580108100800081008002050064013212001902003820038997769989801202008003220080032200382003811802011009910010080000100000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e3a3f51inst 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)9fa1a8a9acc2cfd0d2icache miss (d3)d5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100003050200102160332003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000050200003160222003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000050200002160322003580000102003920039200392003920039
80024200381500000003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000050200003160322003580000102003920039200392003920039
800242003815000002103925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000050200002160222003580000102003920039200392003920039
800242003815000001503925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000050200002160222003580000102003920039200392003920039
8002420038150000039603925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000050200003160222003580000102003920039200392003920039
8002420038150000033903925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100000050200002161442003580000102003920039200392003920039
8002420038150000020703925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000050200003160222003580000102003920039200392003920039
8002420038150000041403925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000050200002160442003580000102003920039200392003920039