Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLT (vector, zero, 8H)

Test 1: uops

Code:

  fcmlt v0.8h, v0.8h, #0
  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)03191e3f4e51inst 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
10042037150091216862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150021016862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203716036116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715008216862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmlt v0.8h, v0.8h, #0
  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)696b6d6edispatch 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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500941968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010013007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010006007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010020007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010010007101161119791100001002003820038200382003820038
102042003715006311968625101001001000010010000500284752120018020037200371842131874510100200100002001000020037200371110201100991001001000010010007102161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e3f4e51inst 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
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000000251196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001010640216221978610000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000000061196862510024101000010100006028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmlt v0.8h, v8.8h, #0
  fcmlt v1.8h, v8.8h, #0
  fcmlt v2.8h, v8.8h, #0
  fcmlt v3.8h, v8.8h, #0
  fcmlt v4.8h, v8.8h, #0
  fcmlt v5.8h, v8.8h, #0
  fcmlt v6.8h, v8.8h, #0
  fcmlt v7.8h, v8.8h, #0
  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)0307080a0b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511811600200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000622580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000001592580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
802042003815000000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000000111511801600200350800001002003920039200392003920039
8020420038150000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000690111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3f51inst 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)72scheduler 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500002292580010108000010800005064000002001902003820038999603100188001020800002080000200382003811800211091010800001000000502019161782003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200190200382003899967310018800102080000208000020038200381180021109101080000100000050201816862003580000102003920039200392003920039
8002420038150000602580010108000010800005064000002001902003820038999603100468010920800002080000200382003811800211091010800001000000502017161742003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200190200382003899960310018800102080000208000020038200381180021109101080000100000050207161752003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200190200382003899960310018800102080000208000020038200381180021109101080000100000050207167152003580000102003920039200392003920039
8002420038150000392580010108000010800005064000002001902003820038999603100188001020800002080000200382003811800211091010800001000000502017161742003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200190200382003899960310018800102080000208000020038200381180021109101080000100000050207166112003580000102003920039200392003920039
8002420038150000392580010108000010800005064000002001902003820038999603100188001020800002080000200382003811800211091010800001000000502017161752003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200190200382003899960310018800102080000208000020038200381180021109101080000100000050207166142003580000102003920039200392003920039
8002420038150000392580010108000010800005064000002001902003820038999603100188001020800002080000200382003811800211091010800001000000502016161652003580000102003920039200392003920039