Apple M1 Microarchitecture Research by Dougall Johnson

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

CLZ (vector, 2S)

Test 1: uops

Code:

  clz v0.2s, v0.2s
  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
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037153611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037153611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  clz v0.2s, v0.2s
  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)031e1f3f4e51inst 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
10204200371505106119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371501806119686251010010010000100100005002847521020018200372003718421318758101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150906119666251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500012419686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
10204200371507206119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371505706119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506606119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371506606119686251010010010000100100005002847521120018200372003718421318745101002041016420010000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100007101161119791100001002003820038200382008520038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b191e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150003306119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200374110021109101010000100039286402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100066402162219786010000102003820038200382003820038
10024200371500048044119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715000606119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200375110021109101010000100036402162219786010000102003820038200382003820038
1002420037150005406119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100106402162219786010000102003820038200382003820038
100242003715000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  clz v0.2s, v8.2s
  clz v1.2s, v8.2s
  clz v2.2s, v8.2s
  clz v3.2s, v8.2s
  clz v4.2s, v8.2s
  clz v5.2s, v8.2s
  clz v6.2s, v8.2s
  clz v7.2s, v8.2s
  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)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150050258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100101115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100501115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100061115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100061115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100031115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100701115118160020035800001002003920039200392003920039
8020420038150029258010810080008100804205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100031115118160020035800001002003920039200902003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160020035800001002003920039200392003920039

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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000050201316112003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815006092580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
800242003815021392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100305020116112003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000104005020116112003580000102003920039200392003920039
800242003815003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001022005020116112003580000102003920039200392003920039
800242003815006092580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381490392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039
80024200381500392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005020116112003580000102003920039200392003920039