Apple M1 Microarchitecture Research by Dougall Johnson

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

REV64 (vector, 2S)

Test 1: uops

Code:

  rev64 v0.2s, v0.2s
  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)030708181e3f4e51inst 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
100420371500006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111784100020382038203820382038
100420371510006116862510001000100026452112018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037160013122168625100010001000264521120182037203715713189510001000100020372037111001100005173116221784100020382038203820382038
1004203715100062168625100010001000264521020182037203715703189510001000100020372037111001100004573116111786100020382038203820382038
100420371500006216862510001000100026452102018203720371570318951000100010002037203711100110000073216111786100020382038203820382038
100420371510006216862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500006216862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715000061168625100010001000264521020182037203715703189510001000100020372037111001100001273116111786100020382038203820382038
100420371500006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500006216862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev64 v0.2s, v0.2s
  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)030b1e3a3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007102161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500300611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150100611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500002511968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715002760611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101160119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)72scheduler 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
1002420037150006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443731876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150036119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037149006119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037211002110910101000010060640216221978610000102003820038200382008520038
1002420037150006119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150106119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150010296119686251001010100001010000502847521120018200372003718443031876710010201000020100002003720037211002110910101000010000640216221978610000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443031876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev64 v0.2s, v8.2s
  rev64 v1.2s, v8.2s
  rev64 v2.2s, v8.2s
  rev64 v3.2s, v8.2s
  rev64 v4.2s, v8.2s
  rev64 v5.2s, v8.2s
  rev64 v6.2s, v8.2s
  rev64 v7.2s, v8.2s
  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)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)9fa0acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180161020035800001002003920039200392003920039
802042003815001529258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500629258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322006920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080918191e1f3f51inst 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)5f696d6edispatch 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)9fa0a1a6a7a8a9acc2cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201716011112003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310069800102080000208000020038200381180021109101080000100000000050201116012122003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201316012132003580000102003920039200392003920039
800242003815000002130392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201316013102003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000003050201116011112003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201316011122003580000102003920039200392003920039
800242003815000002703925800101080000108000050640000020019200382003899961110018800102080000208000020038200381180021109101080000100000000050201316012112003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201116011132003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201216013122003580000102003920039200392003920039
8002420038150000000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100000000050201316012132003580000102003920039200392003920039