Apple M1 Microarchitecture Research by Dougall Johnson

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

CNT (8B)

Test 1: uops

Code:

  cnt 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)0307080a0b18191e1f3a3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000000000073216221786100020382038203820382038
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000000000073216221786100020382038203820382038
100420371500000000061168625100010001000264521120182037203715713189510001000100020372037111001100000000018073216221786100020382038203820382038
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000000000073216221786100020382038203820382038
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000000000073216221786100020382038203820382038
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000000000073216221786100020382038203820382038
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000000000073216221786100020382038203820382038
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000000009073216221786100020382038203820382038
10042037150000000006116862510001000100026452112018203720371571318951000100010002037203711100110000020000073216221786100020382038203820382038
1004203715000000059806116862510001000100026452112018203720371571318951000100010002037203711100110000000000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  cnt 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)030a18191e3f4e51inst 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)9fa8acc5cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371510000611968625101001001000010010000500284752120018200372003718421318745101002001000020010665200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500130611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
102042003715000033611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752120018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020103302010000200372003711100211091010100001000000006404165519786010000102003820038200382003820038
10024200371500100000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006406166519786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006406166519786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475210200542003720037184433187671001020100002010000200372003711100211091010100001000010006406166519786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006405166519786010000102003820038200382003820038
100242003715000000000251196862510010101000010100005028475211200182003720037184433187671001020100002210000200372003711100211091010100001000000006406166619786010000102003820038200382003820038
100242003715000000000103196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006405164519786010000102008520086200382013320038
10024200371500010100061196862510010101000010100005028475211200182008420037184433187851031620100002010000200842003711100211091010100001000000006404166619786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006406165619786010000102003820038200382003820038
10024200371500000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006406166519786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cnt v0.8b, v8.8b
  cnt v1.8b, v8.8b
  cnt v2.8b, v8.8b
  cnt v3.8b, v8.8b
  cnt v4.8b, v8.8b
  cnt v5.8b, v8.8b
  cnt v6.8b, v8.8b
  cnt 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)03080b181e1f3f51inst 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)9fa1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150000420409258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000024029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000004611151181161120035800001002003920039200392003920039
80204200381500003029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000118029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
80204200381500009029258010810280008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001002000011151181161120035800001002003920039200392003920039
802042003815000069029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
802042003815000090292580108100800081008002050064013220019200382003899771299898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
80204200381500000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
80204200381500000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039
80204200381500000029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000000392580010108000010800005064076401200192003820038999631001880010208000020800002003820038118002110910108000010000000050200616432003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200516532003580000102003920039200392003920039
8002420038150000054000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316762003580000102003920039200392003920039
800242003815000001200392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000100050200916642003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200416672003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200416432003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316642003580000102003920039200392003920039
800242003815000000007042580010108000010800005064000011200192003820038999631001880010208000020800002003820038118002110910108000010000000050200416642003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200416342003580000102003920039200392003920039
80024200381500000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000000050200316342003580000102003920039200392003920039