Apple M1 Microarchitecture Research by Dougall Johnson

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

DUP (element, scalar, H)

Test 1: uops

Code:

  dup h0, v0.h[1]
  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)031e3a3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371502621686251000100010002645212018203720371571318951000100010002037203711100110000077516551786100020382038203820382038
100420371502621686251000100010002645212018203720371571318951000100010002037203711100110000077516561786100020382038203820382038
100420371502831686251000100010002645212018203720371571318951000100010002037203711100110000377516551786100020382038203820382038
100420371502851686251000100010002645212018203720371571318951000100010002037203711100110000077516551786100020382038203820382038
1004203715021061686251000100010002645212018203720371571318951000100010002037203711100110000077516551786100020382038203820382038
1004203715026216862510001000100026452120182037203715713189510001000100020372037111001100001277516551786100020382038203820382038
100420371532621686251000100010002645212018203720371571318951000100010002037203711100110000077516551786100020382038203820382038
100420371602831686251000100010002645212018203720371571318951000100010002037203711100110000077516551786100020382038203820382038
1004203716021041686251000100010002645212018203720371571318951000100010002037203711100110000077516551786100020382038203820382038
100420371502621686251000100010002645212018203720371571318951000100010002037203711100110000077516551786100020382038203820382038

Test 2: Latency 1->2

Code:

  dup h0, v0.h[1]
  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)03181e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010043607101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100416507101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001001017707101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000307101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000607101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715001261196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000607101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000307101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000003064031633197860210000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000064031633197860010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100004403064031633197860010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000064031633197860010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000064031633197860010000102003820038200382003820038
1002420037150002141968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000003064031633197860010000102003820038200382003820038
100242003715600611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000064031633197860010000102003820038200382003820038
100242003715000821968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000064031633197860010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000064031633197860010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000064031633197860010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  dup h0, v8.h[1]
  dup h1, v8.h[1]
  dup h2, v8.h[1]
  dup h3, v8.h[1]
  dup h4, v8.h[1]
  dup h5, v8.h[1]
  dup h6, v8.h[1]
  dup h7, v8.h[1]
  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)03080b1e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000182925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010036311151181160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500004092580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001001311151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001005011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)9fa6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015039258001010800001080000506400002001920038200389996310018802042080000208000020038200381180021109101080000100130502017165162003580000102003920039200392003920039
800242003815039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100100502016166162003580000102003920039200392003920039
800242003815039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100100502016166162003580000102003920039200392003920039
8002420038150392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020161616162003580000102003920039200392003920039
8002420038150392580010108000010800005064075620019200382003899963100188001020800002080000200382003811800211091010800001000005020161616162003580000102003920039200392003920039
80024200381503925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010017005020161616162003580000102003920039200392003920039
800242003815039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100213430502016166162003580000102003920039200392003920039
800242003815039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100024050206161662003580000102003920039200392003920039
800242003815039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100030502016166162003580000102003920039200392003920039
800242003815039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100000502016161662003580000102003920039200392003920039