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, vector, 8B)

Test 1: uops

Code:

  dup v0.8b, v0.b[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)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
100420371508216862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371636116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715486116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037156061168625100010001000264521020182037203715713189510001000100020372037111001100007873116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100004573116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715910316862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645210201820372037157131895100010001000203720371110011000015373116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  dup v0.8b, v0.b[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)030f1e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715020611968625101001001000010010000500284752120018200372003718421318764101002001000020010000200372003711102011009910010010000100107341161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100307101161119856100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
1020420037150005361968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100197101161119791100001002003820038200382003820038
102042008415000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100307101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001003337101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150015019686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402163219786010000102003820038200382003820038
1002420037150025319686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000104006402162219786010000102003820038200382003820038
10024200371502434619686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  dup v0.8b, v8.b[1]
  dup v1.8b, v8.b[1]
  dup v2.8b, v8.b[1]
  dup v3.8b, v8.b[1]
  dup v4.8b, v8.b[1]
  dup v5.8b, v8.b[1]
  dup v6.8b, v8.b[1]
  dup v7.8b, v8.b[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)03081e3f51inst 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)9fa0a1a8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
8020420038150001152580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000200111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200381500010342580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000502580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000942580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3a3f51inst 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)5f60696d6edispatch 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)9fa0a1a6a7a8a9acc2cfd5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020191617017262003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020271612029262003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020151613127252003580000102003920039200392003920039
80024200381500000000001272580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020161613029222003580000102003920039200392003920039
80024200381500000000001482580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000005020271615028282003580000102003920039200392003920039
80024200381500000000001022580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020241614023242003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020271611027162003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020171610022282003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020271612027282003580000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000000005020151612028272003580000102003920039200392003920039