Apple M1 Microarchitecture Research by Dougall Johnson

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

RBIT (vector, 16B)

Test 1: uops

Code:

  rbit v0.16b, v0.16b
  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)031e1f3f4e51inst 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
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100003373116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037151506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rbit v0.16b, v0.16b
  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)03080b1e3f4e51inst 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)60696b6d6edispatch 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500024611968625101001001000010010000500284752102001802003720037184210318745101002001000020010000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500006119686251010013010012100100005732847521020018020037200371842103187451010020010000200100002003720037111020110099100100100001000002171021622197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001802003720037184210318745101002001000020010000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018020037200371842103187451010020010000200100002003720037111020110099100100100001000007271021622197911100001002003820038200382003820038
1020420037150004261196862510100100100001001000050028475210200180200372003718421031874510100200100002001000020037200371110201100991001001000010000012971021622197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018020037200371842103187451010020010000200100002003720037111020110099100100100001000002471021622197910100001002003820038200382003820038
102042003715001074719686251010010010000100100005002847521020018020037200371842103187451010020010000200100002003720037111020110099100100100001000001271021622197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001802003720037184210318745101002001000020010000200372003711102011009910010010000100000071021622197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001802003720037184210318745101002001000020010000200372003711102011009910010010000100000371021622197910100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521020018020037200371842103187451010020010000200100002003720037111020110099100100100001000006671021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001002300640216221978610000102003820038200382003820038
10024200371500000005361968625100101010012101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500000006119686251002510100001010000502847521200182003720037184473187671001020100002010000200372003711100211091010100001007890640216221978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100030640216221978610000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000210640216221978610000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037149000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500000006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000690640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rbit v0.16b, v8.16b
  rbit v1.16b, v8.16b
  rbit v2.16b, v8.16b
  rbit v3.16b, v8.16b
  rbit v4.16b, v8.16b
  rbit v5.16b, v8.16b
  rbit v6.16b, v8.16b
  rbit v7.16b, v8.16b
  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)9fa8acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200481500502580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001002911151181620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001001911151181620035800001002003920039200882003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000311151181620035800001002003920039200392003920039
802042008715002925801081008000810080020500640132020019200382003899776100258012020080032200800322003820038118020110099100100800001000011151181620035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010003911151181620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000311151181620035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001001311151181620035800001002003920039200392003920039

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)9fa8a9acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100078005020527532007380000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010100005020516532003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010100005020516352003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010070005020516532003580000102003920039200392003920039
8002420038149039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020516532003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010106005020516562003580000102003920039200392003920039
8002420038150039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010100005020516352003580000102003920039200392003920039
80024200381500134258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010300005020316352003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010103005020516352003580000102003920039200392003920039
8002420038150039258001010800001080000506400001200692003820038999631001880010208000020800002003820038118002110910108000010000005020516532003580000102003920039200392003920039