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, 2D)

Test 1: uops

Code:

  fcmgt v0.2d, v0.2d, #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)031e1f3f4e51inst 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
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000373216111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100002073116111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100002073116111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037160061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111787100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100000073116111823100020382038203820382038
10042037150061168625100010001000264521020182037203715713189510001000100020372037111001100000073116111786100020382038203820382038
10042037150061168625100010001000264521120182037203715713189510001000100020372037111001100001073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt v0.2d, v0.2d, #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)03181e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010003071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100021071011611197910100001002003820038200382003820038
1020420037149006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100015071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102002220037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500061196862510100100100001001000050028525771200182003720037184213187451010020010000200100002003720037111020110099100100100001000150071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030f191e3f4e51inst 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
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001013640216221982210000102003820038200382003820038
100242003715000082196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001036640216121978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001003640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010106085028475210200182003720037184433187671001020100002010000200372003711100211091010100001026640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001003640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001016640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001050640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmgt v0.2d, v8.2d, #0
  fcmgt v1.2d, v8.2d, #0
  fcmgt v2.2d, v8.2d, #0
  fcmgt v3.2d, v8.2d, #0
  fcmgt v4.2d, v8.2d, #0
  fcmgt v5.2d, v8.2d, #0
  fcmgt v6.2d, v8.2d, #0
  fcmgt v7.2d, v8.2d, #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)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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010022111151180161120035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322006020038200389977699898012020080032200800322003820038118020110099100100800001000311151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001001011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001002611151180160120035800001002003920039200392003920039
80204200381500292580108100800081008002050064013220019200382003899776998980120200800322008003220038200381180201100991001008000010063311151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001005011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151183161020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001005011151180160020035800001002003920039200392003920039

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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039151039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001023305020616672003580000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001001805020616662003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996310018800102080000208000020038200381180021109101080000100005020748562003580000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899963100188001020800002080000200382003811800211091010800001059305020616672003580000102003920039200392003920039
80024200381500392580010128000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010468705020716772003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100005020716562003580000102003920039200392003920039
800242003815003925800101080000108000050640000112001920038200389996310018800102080000208000020038200381180021109101080000100305020716762003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100605020616882003580000102003920039200392003920039
800242003815003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100005020716562003580000102003920039200392003920039
8002420038150039258001010800001080000506400000020019200382003899963100188001020800002080000200382003811800211091010800001022005020816762003580000102003920039200392003920039