Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (vector, 2D)

Test 1: uops

Code:

  fcmge v0.2d, v0.2d, v1.2d
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073216111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000004873116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge v0.2d, v0.2d, v1.2d
  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)0304081e3f4e51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715010061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150000103196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
1020420037150000124196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003714900061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
102042003715000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)033f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010659202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715059919687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371506119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmge v0.2d, v1.2d, v0.2d
  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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715043261196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150076196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500611967625101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000710116111979113100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

1000 unrolls and 10 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100030640416431978510000102003820038200382003820038
1002420037150008219687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000102019786640416341978510000102003820038200382003820038
10024200371500058819687251001011100001010304502847680120018200852003718444318767100102010000202000020037200371110021109101010000100100640416431978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640416341978510000102003820038200382003820038
10024200371500126119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640416431978510000102003820038200382003820038
10024200371500010319687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640316341978510000102003820038200382003820038
10024200371500012419687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640416341978510000102003820038200382003820038
100242003715004596119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640416441978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640316341978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640416341978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmge v0.2d, v8.2d, v9.2d
  fcmge v1.2d, v8.2d, v9.2d
  fcmge v2.2d, v8.2d, v9.2d
  fcmge v3.2d, v8.2d, v9.2d
  fcmge v4.2d, v8.2d, v9.2d
  fcmge v5.2d, v8.2d, v9.2d
  fcmge v6.2d, v8.2d, v9.2d
  fcmge v7.2d, v8.2d, v9.2d
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03091e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
802042003815015140258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500063258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9faccfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001018502091671120035080000102003920039200392003920039
80024200381500039258001010800001080000506400002001920038200889996310018800102080000201600002003820038218002110910108000010050209161112200355580000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208009620160000200382003811800211091010800001005020111611720035080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100502071611720035080000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020111611720035080000102003920039200392003920039
8002420038150003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001005020111611820035080000102003920039200392003920039
800242003815000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100502071671120035080000102003920039200392003920039
8002420038150001922580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100502071671120035080000102003920039200392003920039
8002420038150008722580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100502071671120035080000102003920039200392003920039
8002420038150001044258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010050201116111120035080000102003920039200392003920039