Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLP (vector, 4S)

Test 1: uops

Code:

  uaddlp v0.4s, v0.8h
  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)03181e1f3f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371600061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371600061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371510061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
100420371500061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddlp v0.4s, v0.8h
  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)03081e3f4e51inst 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)9fa0a1a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500156119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715002076119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150024299819686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150096119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150036119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000047101161119791100001002003820038200382003820038
10204200371500216119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500186119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640416661978610000102003820038200382003820038
100242003715012726196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516561978610000102003820038200382008620038
1002420037150061196862510010101000010100005028475211200182003720037184453187671001020100002010000200372003711100211091010100001000640616561978610000102003820038200382003820038
10024200371492161196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640416551978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640616661978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516551978610000102003820038200382003820038
10024200371500726196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516441978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640516441978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640616651978610000102003820038200382003820038
100242003715018964196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640616661978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uaddlp v0.4s, v8.8h
  uaddlp v1.4s, v8.8h
  uaddlp v2.4s, v8.8h
  uaddlp v3.4s, v8.8h
  uaddlp v4.4s, v8.8h
  uaddlp v5.4s, v8.8h
  uaddlp v6.4s, v8.8h
  uaddlp v7.4s, v8.8h
  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)0318191e1f3f51inst 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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915000300292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200802312003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920048200489976699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200891500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000010111511801620035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
8020420038150003420292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000360292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f3a3f51inst 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)60696b6d6edispatch 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015100000004500392580010108000010800005064000002001902003820038999631001880010208000020800002003820038118002110910108000010000000050201116642003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000000005020616652003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000000005020516492003580000102003920039200392003920039
80024200381500000000000392580010108000010800005064000012001932003820038100133100188001020800002080000200382003811800211091010800001000000045020616492003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000000005020916552003580000102003920039200392003920039
80024200381500000000000392580010108000010800005064000012001902003820038999631001880010208000020800002003820038118002110910108000010000000050201016662003580000102003920039200392003920039
80024200381500000000150039258001010800001080000506400000200190200382003899963100188001020800002080000200382003811800211091010800001000000005020416552003580000102003920039200392003920039
8002420038150000000000039258001010800001080000506400001200190200382003899963100188001020800002080000200382003811800211091010800001000000305020416542003580000102003920039200392003920039
80024200381500000000000392580010108000010800005064000012001902003820038999631001880010208000020800002003820038118002110910108000010000003050201116562003580000102003920039200392003920039
800242003815000000000005142580010108000010800005064000012001902003820038999631001880010208000020800002003820038118002110910108000010000000050206161272003580000102003920039200392003920039