Apple M1 Microarchitecture Research by Dougall Johnson

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

SHL (vector, 4H)

Test 1: uops

Code:

  shl v0.4h, v0.4h, #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)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
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715010216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715040816862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  shl v0.4h, v0.4h, #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)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)9fa7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000000061196862510100100100001001000050028475212001820037200371842861874110100200100082001000820037200371110201100991001001000010000011171701600198000100001002003820038200382003820038
1020420037150000000658196862510100100100001001000050028475212001820037200371842871874010100200100082001000820037200371110201100991001001000010000011171701600198010100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000084196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715500000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715000000061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150000012061196862510100100100001001000050028475212005420037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820086200382003820038
102042003715000000061196862510100100100001001000050028475212005420037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371500000088156196862510100100100001001015250028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

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)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
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640316221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200375110021109101010000100640216221978610000102003820038200382003820038
1002420037150072619686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200851110021109101010000100640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640216221978610000102003820038200382003820038
1002420037150093319686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100640316221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shl v0.4h, v8.4h, #3
  shl v1.4h, v8.4h, #3
  shl v2.4h, v8.4h, #3
  shl v3.4h, v8.4h, #3
  shl v4.4h, v8.4h, #3
  shl v5.4h, v8.4h, #3
  shl v6.4h, v8.4h, #3
  shl v7.4h, v8.4h, #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)03080b181e1f3f51inst 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)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006115000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511811620035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000000712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
8020420038150000009002580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000100292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511811620035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620105800001002003920039200392003920039
802042003815000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8a9accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100005020017166132003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100005020013161662003580000102003920039200392003920039
80024200381500602580010108000010800005064000012001902003820038999631001880010208000020800002003820038118002110910108000010000502006166132003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010000502005166162003580000102003920039200392003920039
80024200381500735258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000050200161616162003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019020038200389996310018800102080000208000020038200381180021109101080000100005020016166162003580000102003920039200392003920039
800242003815007102580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010000502006161662003580000102003920039200392003920039
8002420038150069925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100005020010161662003580000102003920039200392003920039
800242003815003925800101080000108000050640000120019020038200389996310018800102080000208000020038200381180021109101080000100005020014166162003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003841800211091010800001000050200141616162003580000102003920039200392003920039