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, 4H)

Test 1: uops

Code:

  fcmgt v0.4h, v0.4h, #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)031e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037159611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037153611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150611686251000100010002645211201820372037157131895100010001000203720371110011000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt v0.4h, v0.4h, #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)03040918191e3f4e51inst 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)9fa6a8acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371501000306119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000156119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000156119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119899100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
102042003715000009663119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000156119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371500000156119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000147080301161119791100001002003820038200382003820038
1020420037150000006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372008511102011009910010010000100000071001161119791100001002003820038200382003820038

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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715008919686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100100640316221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100103640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003714906119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100003640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001001300640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100420640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100609640216211978610000102003820038200382003820038
100242003715096119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000102606640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmgt v0.4h, v8.4h, #0
  fcmgt v1.4h, v8.4h, #0
  fcmgt v2.4h, v8.4h, #0
  fcmgt v3.4h, v8.4h, #0
  fcmgt v4.4h, v8.4h, #0
  fcmgt v5.4h, v8.4h, #0
  fcmgt v6.4h, v8.4h, #0
  fcmgt v7.4h, v8.4h, #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)0308090e191e1f3f51inst 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)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)9fa1a6a8a9acc5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057150002000504258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039
8020420038150000012029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000103111511816020035800001002003920039200392003920039
802042003815000000029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013212001920038200389977069989801202008003220080032200382003811802011009910010080000100032003111511816020035800001002003920039200392003920039
802042003815000000029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039
8020420038150000000219258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000000111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000502041633200350080000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010100502031644200350080000102003920039200392003920039
80024200381500392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000502041643200350080000102003920039200392003920039
80024200381500392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010030502051655200350080000102003920039200392003920039
80024200381500392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000502041654200350080000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000502071677200350080000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000502051633200350080000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010100502031634200350080000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000502051655200350080000102003920039200392003920039
80024200381500392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010100502041644200350080000102003920039200392003920039