Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTXN (vector, 2D)

Test 1: uops

Code:

  fcvtxn v0.2s, v0.2d
  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)0307080b18191e1f3a3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372410000000612547251000100010003981600301830373037241432895100010001000303730371110011000000003073316222626100030383038303830383038
100430372400000000822547251000100010003981600301830373037241432895100010001000303730371110011000000200073116112629100030383038303830383038
1004303723000001200612547251000100010003981600301830373037241332895100010001000303730371110011000000002230073116222626100030383038303830383038
10043037241000033600612547251000100010003981601301830373037241332895100010001000303730371110011000000103073116112629100030383038303830383038
100430372400000000612547251000100010003981601301830373037241432895100010001000303730371110011000000003073116112629100030383038303830383038
100430372410000000822547251000100010003981600305430373037241432895100010001000303730371110011000000000073116222629100030383038303830383038
100430372310000000612547251000100010003981600301830373037241332895100010001000303730371110011000000803075216112629100030383038303830383038
1004303723000009006125472510001000100039816013018303730372414328951000100010003037303711100110000001400077116112629100030383038303830383038
100430372410000000612547251000100010003981600301830373037241432895100010001000303730371110011000000000073116112629100030383038303830383038
100430372300000000612547251000100010003981601301830373037241332895100010001000303730371110011000000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtxn v0.2s, 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): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000013800612954725101291001001610610000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000028430071011611296330100001003003830086300383003830038
1020430037225000014100612954725101001001000010010000500427716013001830086301322826832874510100200100002001000030037300371110201100991001001000010000000030071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716003001830037300372826432874510100216100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000001000071011611296330100001003003830038300383003830038
10204300372250000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372240000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830299300383008230038
10024300852410000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372410000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtxn v0.2s, v8.2d
  fcvtxn v1.2s, v8.2d
  fcvtxn v2.2s, v8.2d
  fcvtxn v3.2s, v8.2d
  fcvtxn v4.2s, v8.2d
  fcvtxn v5.2s, v8.2d
  fcvtxn v6.2s, v8.2d
  fcvtxn v7.2s, v8.2d
  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)0307080a1e1f3f51inst 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)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815510100183425801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020089
8020420039156101003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
8020420039155101003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391551010071825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611201170800001002004020040200402004020040
8020420039161101003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010010111511811611200360800001002004020040200402004020040
8020420039155101003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391561011203025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391561010024825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010010111511811611200360800001002004020040200402004020040
802042003915610149206426801161008001610080028500640196020029200482004999769998680128200800382008003820049200481180201100991001008000010000222512822332200840800001002005020049200492004920049
80204200481550000015026801161008001610080028500640196120029200482004999769998680128200800382008003820048200481180201100991001008000010000222512822322200450800001002004920049200502004920049

1000 unrolls and 10 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502012161010200360080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502013161210200360080000102004020040200402004020040
800242003915600040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020616127200360080000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080106200392003911800211091010800001000000502011161212200360080000102004020040200402004020040
80024200391610004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000100502011161110200360080000102004020040200402004020040
80024200391550002442580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000350201316129200360080000102004020040200402004020040
80024200391550034025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000003502012161212200360080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502010161212200360080000102004020040200402004020242
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502011161111200360080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502012161211200360080000102004020040200402004020040