Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGT (vector, zero, 4S)

Test 1: uops

Code:

  fcmgt v0.4s, v0.4s, #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)03191e1f3f4e51inst 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
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720701571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt v0.4s, v0.4s, #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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150816119686251010010010000100100005002847521200182003720037184283187451010020210000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101162119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150126119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
1020420037150276119686251010010010000105100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715606119686251010010010000100100005002847521200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521200222003720037184243187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500137196862510010101000010100005028475210200182003720037184433187671001020101692010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010101505028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715027061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715034261196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000810100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmgt v0.4s, v8.4s, #0
  fcmgt v1.4s, v8.4s, #0
  fcmgt v2.4s, v8.4s, #0
  fcmgt v3.4s, v8.4s, #0
  fcmgt v4.4s, v8.4s, #0
  fcmgt v5.4s, v8.4s, #0
  fcmgt v6.4s, v8.4s, #0
  fcmgt v7.4s, v8.4s, #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)03191e3f51inst 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)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200481500029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000579258010810080008100800205006401320200192003820038997799989801202008003220080032200382003811802011009910010080000100001115118016220035800001002003920039200392003920039
802042003815002429258010810080008100800205006407561200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500629258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815010694258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
8020420038150038429258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500629258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b1e3a3f51inst 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)9fa1a6a8accficache miss (d3)itlb miss (d4)d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000035020009164220035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000035020004164220035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000035020002162420035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020002162420035080000102003920039200392003920039
800242003815000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000155020002162420035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000035020002164420035080000102003920039200392003920039
80024200381500009039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020004164220035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020002166620035080000102003920039200392003920039
80024200381500000039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001000005020004162420035080000102003920039200392003920039
800242003815000000392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000050200031624200354080000102003920039200392003920039