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, 8H)

Test 1: uops

Code:

  rev64 v0.8h, v0.8h
  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
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004207315061168625100010001000264521120182037203715713189510001000100020372037111001100001273116111786100020382038203820382038
1004203715061168625100010001000264521120182037203715713189510001000100020372037111001100002473116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110002073116111786100020382038203820382038
1004203716126116862510001000100026452112018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
1004203715025116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112022203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev64 v0.8h, v0.8h
  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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521120018200372003718428618740101002001000820010008200372003711102011009910010010000100001117182161119800100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100001117181161119801100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428718741101002001018020010008200372003711102011009910010010000100001117181161119800100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428618740101002001000820010008200372003711102011009910010010000100001117171161119801100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718428618741101002001000820010008200372003711102011009910010010000100001117181161119801100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100001117171161119800100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428718741101002001000820010008200372003711102011009910010010000100001117171161119800100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428618740101002001000820010008200372003711102011009910010010000100001117181161119801100001002003820038200382003820038
102042003715096119686251010010010000100100005002847521120018200372003718428718741101002001000820010008200372003711102011009910010010000100001117171161119800100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718428618741101002001000820010008200372003711102011009910010010000100131117171161119800100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715010519686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000104410640316221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371506119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev64 v0.8h, v8.8h
  rev64 v1.8h, v8.8h
  rev64 v2.8h, v8.8h
  rev64 v3.8h, v8.8h
  rev64 v4.8h, v8.8h
  rev64 v5.8h, v8.8h
  rev64 v6.8h, v8.8h
  rev64 v7.8h, v8.8h
  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)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)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381503292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
802042003815006942580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381500502580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381500292580108101800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000111511801620035800001002003920039200392003920039

1000 unrolls and 10 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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020616552003580000102003920039200392003920039
8002420038150001342580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020316352003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020316532003580000102003920039200392003920039
800242003815100392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020516352003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020316352003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020516532003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020516532003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020516352003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020516352003580000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002080000200382003811800211091010800001000005020516532003580000102003920039200392003920039