Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLT (scalar, zero, S)

Test 1: uops

Code:

  fcmlt s0, s0, #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)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
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073316111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371612821686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150821686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmlt s0, s0, #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)0318191e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020178200371110201100991001001000010071021611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001066020037200371110201100991001001000010071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038
10204200371500002511968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371504806119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402163319786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
1002420037150606119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786210000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402163319786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
100242003715021161219653631001010100001510304612851313120126201802003718453318767100102010331201000020084200841110021109101010000100006402162119786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100007034162219786010000102003820038200382003820038
100242003715035706119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmlt s0, s8, #0
  fcmlt s1, s8, #0
  fcmlt s2, s8, #0
  fcmlt s3, s8, #0
  fcmlt s4, s8, #0
  fcmlt s5, s8, #0
  fcmlt s6, s8, #0
  fcmlt s7, s8, #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)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)cdcfd6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571504682925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020095800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000129111511816020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899946998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
80204200381502672925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308181e1f3f51inst 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)696b6d6edispatch 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150007203925800101080000108000050640000200190200382003899963100188001020800002080000200382003811800211091010800001000000050201016532003580000102003920039200392003920039
800242003815000180392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020416532003580000102003920039200392003920039
80024200381500090392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020316532003580000102003920039200392003920039
80024200381500060392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020516532003580000102003920039200392003920039
80024200381500000392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020516532003580000102003920039200392003920110
80024200971500090392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020516532003580000102003920039200392003920039
8002420038151003870392580010108000010800005064000020019020038200389996310018800102080000208000020038200871180021109101080000100000005020516542003580000102003920039200392003920039
80024200381500000392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020516532003580000102003920039200392003920039
800242003815000210392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020516352003580000102003920039200392003920039
80024200381500000392580010108000010800005064000020019020038200389996310018800102080000208000020038200381180021109101080000100000005020516552003580000102003920097200392003920039