Apple M1 Microarchitecture Research by Dougall Johnson

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

REV64 (vector, 8B)

Test 1: uops

Code:

  rev64 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)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
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000373216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004207315106116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000373216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110001073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  rev64 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)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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071023311197910100001002003820038200382003820038
10204200371503110519686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197912100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200842003718421318745101002001000020010000200372003711102011009910010010000100000071013211197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150010319686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038

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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000240611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000004506311966425100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
100242003715000000094319686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001000002106402162219786010000102003820038200382003820038
1002420037150000000611968625100101110000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  rev64 v0.8b, v8.8b
  rev64 v1.8b, v8.8b
  rev64 v2.8b, v8.8b
  rev64 v3.8b, v8.8b
  rev64 v4.8b, v8.8b
  rev64 v5.8b, v8.8b
  rev64 v6.8b, v8.8b
  rev64 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)03091e3f51inst 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)9fa6a8acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715004829258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381490029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
802042003815003029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa0a1a8a9accdcfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500123925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000100050200216422003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038100293101268001020800002080000200382003811800211091010800001000300050200216242003580000102003920039200392003920039
80024200381500026425800101080000108000050640000120019200382003899963100468001020800002080000200382003811800211091010800001000000050200416242003580000102003920039200392003920039
800242003815000149225800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000050200616442003580000102003920039200392003920039
80024200381500012325800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000050200416422003580000102011220039200882003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000050200416422003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000050200216242003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000050200416242003580000102003920039200392003920039
80024200381501012325800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000103050200216422003580000102003920039200392003920039
8002420038150003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000000050200416242003580000102003920039200392003920039