Apple M1 Microarchitecture Research by Dougall Johnson

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

REV32 (vector, 8H)

Test 1: uops

Code:

  rev32 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)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
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371512611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
10042037153611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037153611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951152100010002037203711100110000073116111786100020382038203820382038
10042037166611686251000100010002645212018203720371571318951000100010002037203711100210000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev32 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)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)60696b6d6edispatch 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000002071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000003071011611197910100001002003820038200382003820038
1020420037150006119686641010010010000100100005002847521120018020037200371842131874510100204100002001000020037200371110201100991001001000010000229710141111979126100001002003820038200382003820038
1020420037150012611968625101001001000010010000522284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500285217912001802003720037184213187451010020010000200100002003720037111020110099100100100001000002071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000001071011611197910100001002003820038200382003820038
1020420037150001031968625101001001000010010152500284752102001802003720132184213187451041720010000200100002003720037111020110099100100100001002203071011611197910100001002008520038200382003820038
102042003715000611968625101001001000010010000500284752112001802003720037184213187451010020010000200100002003720037111020110099100100100001000001071011611197910100001002003820038200382003820038

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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640316221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
10024200371500441196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000003640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010002700640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100034090640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001020100640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev32 v0.8h, v8.8h
  rev32 v1.8h, v8.8h
  rev32 v2.8h, v8.8h
  rev32 v3.8h, v8.8h
  rev32 v4.8h, v8.8h
  rev32 v5.8h, v8.8h
  rev32 v6.8h, v8.8h
  rev32 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500292580108100800081008002050064075612001920038200389977699898012020080032200800322003820038118020110099100100800001000101115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815092925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000511115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920088200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000201115118016020035800001002003920039200392003920039
80204200731500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000631115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000601115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f3f51inst 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)9fa1a7a8acc2cfd0d5d6d9ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020021602420035780000102003920039200392003920039
800242003815000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000005020031604220035780000102003920039200392003920101
8002420038150000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100004505020081604420035780000102003920039200392003920039
800242003815000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000005020021602420035780000102003920039200392003920039
800242003815000000392580010108000010800005064000011200192003820038999631001880010208000020800002003820038118002110910108000010000005020041606320035780000102003920039200392003920039
800242003815000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000005020041604220035780000102003920039200392003920039
800242003815000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020041604420035080000102003920039200392003920039
800242003815000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020021604220085080000102003920039200392003920039
800242003815000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000005020041602420035080000102003920039200392003920039
800242003815000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020021604220035080000102003920039200392003920039