Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZS (vector, fixed-point, 2S)

Test 1: uops

Code:

  fcvtzs v0.2s, v0.2s, #3
  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)0308091e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037260006125472510001000100039816003018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
10043037260006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372600248225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037260006125472510001000100039816003018303730372414328951000100010003037303711100110002073116112629100030383038303830383038
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400126125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372500126125472510001000100039816003018303730372414328951000100010003037303711100110001373116112629100030383038303830383086
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000673116112629100030383038303830383038
100430372300014525472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzs v0.2s, v0.2s, #3
  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)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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100001037102162229633000100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007102162229633000100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000037102162229633000100001003003830038300383003830038
10204300372330000300612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007102162229705000100001003003830038300383003830038
10204300372330000000612954725101001021000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007105162229633000100001003003830038300383003830038
102043003723310000007262954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007102162229633000100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007102162229633000100001003003830038300383003830038
10204300372330000600612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007102162229633000100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007102162229633000100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007102162229633000100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722500000081006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100806402162229629010000103003830038300383003830038
10024300372250000003006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000604277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402165229629010000103008630134300383003830038
10024300372251020000006129547251001010100001010000604277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100071010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
10024300372250000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100006402162229631010000103003830038300383003830038
1002430037225000000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010022642583091106329936210000103041230467304633046330465

Test 3: throughput

Count: 8

Code:

  fcvtzs v0.2s, v8.2s, #3
  fcvtzs v1.2s, v8.2s, #3
  fcvtzs v2.2s, v8.2s, #3
  fcvtzs v3.2s, v8.2s, #3
  fcvtzs v4.2s, v8.2s, #3
  fcvtzs v5.2s, v8.2s, #3
  fcvtzs v6.2s, v8.2s, #3
  fcvtzs v7.2s, v8.2s, #3
  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)03080e1e1f3f51inst 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)9fa8acb6c5branch mispredict (cb)cdcfd2d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915500177030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391550039030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151540160020036800001002004020040200402004020040
802042003915500279030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039161000030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915500297030258010810080008100800205006401321200200200392003999776999080120200800322008014420039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915605303030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155003720220258010810080008100800285006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915500120315258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039155003030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391550021030258010810080008100800205006401320200200200392003999776999080120200800382008003820088200491180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090f18191e3f51inst 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)6061696d6edispatch 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)9fa8accfd0d2d5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115500000402580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010005030501616001572007480000102004020040200402004020040
800242003915500000402580010108000010800005064000005200202003920039999631001980010208000020800002003920039118002110910108000010005032508160017172003680000102004020040200402004020040
800242003915600000402580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010005030501716001772003680000102004020040200402004020040
8002420039155000004462580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010005030501516018172003680000102004020040200402004020040
80024200391550000340258001010800001080000506400000520020200392003999963100198001020800002080000200392003911800211091010800001000503050616006172003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100050305017160017172003680000102004020040200402004020040
800242003915600000402580010108000010800005064000005200202003920039999631001980010208000020800002003920039118002110910108000010005030541716008172003680000102004020040200402004020040
8002420039155000094025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100050305017160017172003680000102004020040200402004020040
80024200391550000040258001010800001080000506400001020020200392003999963100198001020800002080000200392003911800211091010800001000503054816001782003680000102004020040200402004020040
8002420039155000002302580010108000010800005064000005200202003920039999631001980010208000020800002003920039118002110910108000010005030501716008172003680000102004020040200402004020040