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, zero, S)

Test 1: uops

Code:

  fcmgt 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)03080b3f4e51inst 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
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371501611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720731571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt 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)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)9fa1a8a9cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150821968625101001001000010010000534284878512001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000107101161119791100001002003820038200382003820038
1020420037149611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037150611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371501241968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa1a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150540611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150180611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371504830611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000306402162219786010000102003820038200382003820038
1002420037150180611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150150611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150002511968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmgt s0, s8, #0
  fcmgt s1, s8, #0
  fcmgt s2, s8, #0
  fcmgt s3, s8, #0
  fcmgt s4, s8, #0
  fcmgt s5, s8, #0
  fcmgt s6, s8, #0
  fcmgt 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)03080b1e3f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500002925801081008000810080020500640132020019200382003899776998980120200802292008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
8020420038150000256925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151181160020035800001002003920039200392003920039
802042003815000015125801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815000512925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015001803925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502005168520035080000102003920039200392003920039
8002420038150031203925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502037166520035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502006166520035080000102003920039200392003920039
800242003815001803925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502005165620035080000102003920039200392003920039
800242003815000017925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502006166520035080000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001003502006168720035080000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000502008166720035080000102003920039200392003920039
8002420038150045070425800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001020502006165620035080000102003920039200392003920039
8002420038150015303925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502006167520035080000102003920039200392003920039
80024200381510003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000502005168520035080000102003920039200392003920039