Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (scalar, zero, D)

Test 1: uops

Code:

  fcmeq d0, d0, #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
100420371512611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371521821686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371569611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037156611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715129611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037150611686251000100010002645212018203720371571318951000100010002037203711100110000973116111786100020382038203820382038
10042037160611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq d0, d0, #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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003718700611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150420611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715060611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715060611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110202100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752102005420037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500103196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000066404165519786010000102003820038200382003820038
10024200371500611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010010666406165619786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006406166519786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001002006405165519786010000102003820038200382003820038
100242003715006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000102001746406166519848010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001001006405165519786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006404165519786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001001066405164519786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000006406166619786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000036405166419786210000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmeq d0, d8, #0
  fcmeq d1, d8, #0
  fcmeq d2, d8, #0
  fcmeq d3, d8, #0
  fcmeq d4, d8, #0
  fcmeq d5, d8, #0
  fcmeq d6, d8, #0
  fcmeq d7, d8, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03080b18191e1f3a3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150000000063225801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000002000111511801600200350800001002003920039200392003920039
8020420038150000000017825801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000030111511801600200350800001002003920039200392003920039
8020420038150000012002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000015925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000007125801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000013425801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
8020420038150000000013825801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801600200350800001002003920039200392003920039
802042003815000000002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000000000111511801601200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa0a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500001922580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100021005020633342003580000102003920039200392003920039
800242003815021081258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010013005020416432003580000102003920039200392003920039
8002420038150000118258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000005020416432003580000102003920039200392003920039
800242003815000060258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010003005020416342003580000102003920039200392003920039
800242003815000062258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000005089416432003580000102003920039200392003920039
8002420138150001239258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000005020316342003580000102003920039200392003920039
8002420038150000206258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000005020316342003580000102003920039200392003920039
8002420038150000799258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000005020416432003580000102003920039200392003920039
800242003815000060258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000005020316342003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010000005020316342003580000102003920039200392003920039