Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDLP (vector, 1D)

Test 1: uops

Code:

  saddlp v0.1d, v0.2s
  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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715066168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  saddlp v0.1d, v0.2s
  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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500001241968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000821968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500002511968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000671011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000371011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03040b18191e3f4e51inst 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
10024200371501000010319686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150001068419686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150000031215419686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037149000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
10024200371500000017019686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  saddlp v0.1d, v8.2s
  saddlp v1.1d, v8.2s
  saddlp v2.1d, v8.2s
  saddlp v3.1d, v8.2s
  saddlp v4.1d, v8.2s
  saddlp v5.1d, v8.2s
  saddlp v6.1d, v8.2s
  saddlp v7.1d, v8.2s
  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)030b1e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150000712580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392014720039
8020420038151000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000010001115171016020035800001002003920039200392003920039
80204200381500001782580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392003920039
80204200381500004512580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200382180201100991001008000010000000001115118065020035800001002003920039200392003920039
80204200381500001152580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392003920039
80204200381500002192580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030409191e1f3a3f51inst 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)9fa0a6a8a9accfd2icache miss (d3)itlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500000008725800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000005021001143114162003580000102003920039200392003920039
80024200381501100008725800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000005021001173117142003580000102003920039200392003920039
8002420038150110000872580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000000502000093012182003580000102003920039200392003920039
80024200381501100009925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000047050210011429617172003580000102003920039200392003920039
8002420038150110000872580010108000010800005064000020019200862013799963100188001020800002080000200382003811800211091010800001000000502100117591882008180000102003920039200392003920039
80024200381501110132015025800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000035021001143017112003580000102003920039200392003920039
80024200381501100008725800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000005021001143017192003580000102003920039200392003920039
800242003815011000012925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000005021001172914172003580000102003920039200392003920039
800242003815011000023625800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000005021001143017182003580000102003920039200392003920039
8002420038150110000872580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000000502100114301782003580000102003920039200392003920039