Apple M1 Microarchitecture Research by Dougall Johnson

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

SSHR (vector, D)

Test 1: uops

Code:

  sshr d0, d0, #3
  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)03071e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203716006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020842038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
1004203715008216862510001000100026452120182037203715713189510001000100020372037111001100004073116111786100020382038203820382038
1004203715006116862510001000100026452120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  sshr d0, d0, #3
  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)03080918191e1f3f4e51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000001031968625101001001000010010000500284752102001820037200371842871874110100200100082001000820037200851110201100991001001000010000010000071011612197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000001731967525101161001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
1020420037149000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000001471968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820085
10204200371560000001151968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000002231968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
1020420037150000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000150611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500001321968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150009611968625100351010000101000050284752120018200372003718443818767100102010000201000020037200371110021109101010000100000006402162219786010000102003820085200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000611968625100101010000101015050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000611967525100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  sshr d0, d8, #3
  sshr d1, d8, #3
  sshr d2, d8, #3
  sshr d3, d8, #3
  sshr d4, d8, #3
  sshr d5, d8, #3
  sshr d6, d8, #3
  sshr d7, d8, #3
  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)031e1f3f5051inst 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)9fa9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571512102902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150902902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
802042003815033002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
802042003815015050402580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
8020420038150002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381503002902580108100800081008002050064013212001920038200389977699898012020080032200801332003820038118020110099100100800001000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)5f696d6edispatch 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)9fa8accfd0icache miss (d3)d5d6daddinst fetch restart (de)dfe0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000037203925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502400101602232003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100350240021602632003580000102003920039200392003920039
800242003815000003090602580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050240031603632003580000102003920039200392003920039
80024200381490000003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001070650240031602632003580000102003920039200392003920039
800242003815000003180392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050240061602232003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050240021602232003580000102003920039200392003920039
8002420038150000090392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050240031606332003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050240021602232003580000102003920039200392003920039
8002420038150000042352392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050240021602232003580000102003920039200392003920039
8002420038150000030832580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050240021606232003580000102003920039200392003920039