Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGT (scalar, S)

Test 1: uops

Code:

  fcmgt s0, s0, s1
  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)696d6edispatch 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
100420371515611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037153611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371515611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371548611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371515611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371524611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371551611687251000100010002646802018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt s0, s0, s1
  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)5e60696d6edispatch 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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371503961196872510100100100001001000050028476801120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820085200382003820038
1020420037150061196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150961196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800020018200372003718422318818101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
10204200371500536196872510100100100001001000050028476800120018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150961196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150661196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476800020018200372003718422318745101002001000020020000200372003711102011009910010010000100100071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03091e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100200640216221978510000102003820038200382003820038
1002420037150009431968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000126640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100003640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010020168640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680200182003720037184443187671001020100002020000200372003711100211091010100001000099640216221978510000102003820038200382003820038
100242003715001326119687251001010100001010000722847680200182003720037184443187671001020100002020000200372003711100211091010100001000075640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000153640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768020018200372003718444318767100102010000202000020084200371110021109101010000100203640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmgt s0, s1, s0
  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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150611968725101001001000010010000500284768012001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371506119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010001571011611197910100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001001371011611197910100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001005071023711197910100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001003071011611197910100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001001071011611197910100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371506119687251010010010000116100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010009671011611197910100001002003820038200382003820038
1020420037150611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000671011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b191e3f4e51inst 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)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
100242003715000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000105406402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010136402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010166402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001802003720037184443187671001020100002020000200372003711100211091010100001045876402162219785010000102008520038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010106402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000101006402162219785010000102003820038200382003820038
10024200371500006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010106402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200180200372003718444318767100102010000202000020037200371110021109101010000104806402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmgt s0, s8, s9
  fcmgt s1, s8, s9
  fcmgt s2, s8, s9
  fcmgt s3, s8, s9
  fcmgt s4, s8, s9
  fcmgt s5, s8, s9
  fcmgt s6, s8, s9
  fcmgt s7, s8, s9
  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)030918191e3f51inst 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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000004025801001008000011180000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001001300511021611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001000511011611200350800001002003920039200392003920039
80204200381500000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100049820511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200852003899733999680100200800002001600002003820038118020110099100100800001004812300511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001001000511011611200350800001002003920039200392003920039
802042003815000004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000001511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)033f51inst 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)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
800242004715039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000100050201116222003580000102003920039200392003920039
800242003815039258001010800001080000506400001200190200382003899963100188001020800002016000020038200381180021109101080000103165020616222003580000102003920039200392003920039
80024200381503925801971080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010235020216632003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020616622003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020216262003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020616622003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020216222003580000102003920039200392003920039
80024200381503925800101080000108000050640000120019020038200389996310018800102080000201600002003820038118002110910108000010005020216262003580000102003920039200392003920039