Apple M1 Microarchitecture Research by Dougall Johnson

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

SHL (scalar, D)

Test 1: uops

Code:

  shl 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)030b1e3f4e51inst 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
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111853100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150156116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160061168625100010001000264521120182037203715713189510001000100020372037111001100002773116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  shl 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)033f4e51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150103196862510100100100001001000050028475212001820037200371842861874110100200100082001000820037200371110201100991001001000010000011171701600198000100001002003820038200382003820038
102042003715061196862510127100100001001000050028475212001820037200371842871874010100200100082001000820037200371110201100991001001000010002010011171701600198000100001002003820038200382003820038
102042003714961196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010006000071011611197910100001002003820038200382003820038
102042003715061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150124196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037150103196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010003000071011611197910100001002003820038200382003820038
102042003715061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715061196862510100100100001001000050028475212001820037200371842131874510100200100002001000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640316221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500519196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371501861196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  shl d0, d8, #3
  shl d1, d8, #3
  shl d2, d8, #3
  shl d3, d8, #3
  shl d4, d8, #3
  shl d5, d8, #3
  shl d6, d8, #3
  shl 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): 0.2506

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)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)9fa8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200671501829258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200282004820049997699986801282008003820080038200482004811802011009910010080000100022251291231120045800001002004920049200492004920049
8020420048150064268011610080016100800285006401961200282004820048997699986801282008003820080038200482004811802011009910010080000100022251281231120045800001002004920049200492004920049
802042004815001482680116100800161008002850064019612002820048200499976109986801282008003820080038200492004911802011009910010080000100022251281231120045800001002004920049200492004920049
8020420048150064268011610080016100800285006401961200282004820048997699986801282008003820080038200492004911802011009910010080000100022251291231120046800001002005020050200502004920049
8020420049150064278011610080016100800285006401961200412004820048997699986801282008003820080038200482004911802011009910010080000100022251281231120045800001002004920049200492004920049
80204200491500642680116100800161008002850064019602002820048200489976109986801282008003820080038200492004911802011009910010080000100022251281231120046800001002004920049200502005020049
8020420048150064278011610080016100800285006401960200282004920049997699986801282008003820080038200482004811802011009910010080000100022251281232220044800001002004820048200482004820048
8020420047150075278010010080000100800005006400001200282004720047997169993801002008000020080000200472004711802011009910010080000100211151202242220044800001002004820048200482004820048
8020420047150075278010010080000100800005006400001200282004720047997169993801002008000020080000200472004711802011009910010080000100011151202242220044800001002004820048200482004820048

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f3a3f51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000000062258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050202916202520035080000102003920039200392003920039
8002420038149000000000081258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050202916192520035080000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000000050202616123020035080000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050202616272520035080000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050203516272620035080000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050203316291620035080000102003920039200392003920039
8002420038155000000000039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050202916271520035080000102003920039200392003920039
8002420038150000000000039258001010800001080000506400000200190200882003899963100188001020800002080000200382003811800211091010800001000000050202916272720035080000102003920039200392003920039
80024200381500000000000275258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000050202616251520035080000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000000050202916132520035080000102003920039200392003920039