Apple M1 Microarchitecture Research by Dougall Johnson

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

REV16 (vector, 8B)

Test 1: uops

Code:

  rev16 v0.8b, v0.8b
  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)03181e3f4e51inst 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
100420371600611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715101031686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500821686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715015611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371600841686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073216111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev16 v0.8b, v0.8b
  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)030b181e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000132094319686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820086
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150000886119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372008531102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150003025119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

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)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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000300611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000001620611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402172219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000240611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000003900611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000016402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
100242003715000003540611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev16 v0.8b, v8.8b
  rev16 v1.8b, v8.8b
  rev16 v2.8b, v8.8b
  rev16 v3.8b, v8.8b
  rev16 v4.8b, v8.8b
  rev16 v5.8b, v8.8b
  rev16 v6.8b, v8.8b
  rev16 v7.8b, v8.8b
  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)0308090b18191e3f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150000006292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118116020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500000012292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038149000009292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708181e3f51inst 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
800242005115000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020916772003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020616642003580000102003920039200392003920039
8002420038150000047325800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020516562003580000102003920039200392003920039
8002420038149000183925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020516562003580000102003920039200392003920039
8002420038150000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100125020516562003580000102003920039200392003920039
8002420038150000041925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020616652003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020516882003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020517572003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020516452003580000102003920039200392003920039
800242003815000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010005020616572003580000102003920039200392003920039