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, 16B)

Test 1: uops

Code:

  rev32 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)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
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073316111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev32 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)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)6061696b6d6edispatch 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371506119686251010010010000100100005002847521052001802003720037184213187451010020010000200100002003720037111020110099100100100001000071052161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521102001802003720037184213187451010020010000200100002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521102001802003720037184213187451010020010000200100002003720037111020110099100100100001000071051161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521052001802003720037184213187451010020010000200100002003720037111020110099100100100001000071051161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521102001802003720037184213187451010020010000200100002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
102042003715072619686251010010010000100100005002847521102001802003720037184213187451010020010000200100002003720037111020110099100100100001000071051161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521052001802003720037184213187451010020010000200100002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521052001802003720037184213187451010020010000200100002003720037111020110099100100100001000071051161119791100001002003820038200382003820038
10204200371496119686251010010010000100100005002847521102001802003720037184213187451010020010000200100002003720037111020110099100100100001000071001161119791100001002003820038200382003820038
10204200371506119686251010010010000100100005002847521052001802003720037184213187451010020010000200100002003720037111020110099100100100001000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080a0b18191e1f3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000004806119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200841110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
10024200371500000014106119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000036402162219786010000102003820038200382003820038
1002420037150000005106119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
10024200371500000010506119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
10024200371500000011706119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718457318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev32 v0.16b, v8.16b
  rev32 v1.16b, v8.16b
  rev32 v2.16b, v8.16b
  rev32 v3.16b, v8.16b
  rev32 v4.16b, v8.16b
  rev32 v5.16b, v8.16b
  rev32 v6.16b, v8.16b
  rev32 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)0318191e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500015292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920089
80204200381501215292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815000447292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132200192003820038997726998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038149000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391502217252580010108000010800005064000002001920090200389996310018800102080000208000020038200381180021109101080000103350201160112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100650201163112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800982080098201242009111800211091010800001002450201160112003580000102003920039200392003920039
800242003815010392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039
80024200381500132392580104108000010800005064000002001920038200389996310018800102080000208000020088200381180021109101080000100350201160112003580000102003920039200392003920039
800242003815000392580010108000010800005064152802001920038200389996310018800102080000208000020038200381180021109101080000100350201160112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001001550201160112003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001001250201160112003580000102003920039200392003920039
800242003815009602580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050201160112003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000102050201160112003580000102003920039200392003920039