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, 2D)

Test 1: uops

Code:

  saddlp v0.2d, v0.4s
  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
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100009373216221786100020382038203820382038
1004203715010516862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371566116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715013116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  saddlp v0.2d, v0.4s
  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)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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371506361196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371502761196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371502161196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150961196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371502761196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715025261196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090a0b181e1f3f4e51inst 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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037149000001805361968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000060611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010010006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371845631876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
1002420037150000002430611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  saddlp v0.2d, v8.4s
  saddlp v1.2d, v8.4s
  saddlp v2.2d, v8.4s
  saddlp v3.2d, v8.4s
  saddlp v4.2d, v8.4s
  saddlp v5.2d, v8.4s
  saddlp v6.2d, v8.4s
  saddlp v7.2d, v8.4s
  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)031e3f5051inst 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)9fa0acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715032902580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815002902580108100800081008002050064013212001920038200389977699898012020080133200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815002902580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815002902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150182902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001004011151180160020035800001002003920039200392003920039
80204200381506342802580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802052003814902902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815062902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815092902580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

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)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)9fa8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050207160462003580000102003920039200392003920039
800242003815007042580010108000010800005064000002001920038200389996310072800102080000208000020038200381180021109101080000100050206160562003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050206160462003580000102003920039200392003920039
80024200381500392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050206160642003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050204160462003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050205160662003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050205160642003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050206160562003580000102003920039200392003920039
8002420038150216392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050204160462003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050206160462003580000102003920039200392003920039