Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (vector, fixed-point, 4S from 4S)

Test 1: uops

Code:

  scvtf v0.4s, v0.4s, #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)03181e3f4e51inst 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
10043037220029325472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100010003037303711100110000073116122629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722008225472510001000100039816013018303730372414328951000100010003037303711100110000073116212629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722008225472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125382510001000100039816013018303730372414328951000100011613037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018307330372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004308523006125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf v0.4s, v0.4s, #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)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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372254261295472510100100100001001000050042771601300183003730037282716287411010020010008200100083003730037111020110099100100100001000001117180160029645100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282717287401010020010008200100083003730037111020110099100100100001000001117170160029645100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
102043003722515631295472510100100100001001000050042771601300183003730037282643287451041020010000200100003003730037111020110099100100100001000040007101161129633100001003003830038300383003830038
10204300372252461295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372251861295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101162129633100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000103295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000306402162229629010000103003830038300383003830085
100243003722500001200103295472510012121000010100005042771601300183003730037282863287671001220100002010000300373003711100211091010100001000010006402162229629010000103003830038300383003830038
100243003722400001200103295472510010101000010100005042771601300183003730037282863287671001220100002010000300373003711100211091010100001000010006402162229631010000103003830038300383003830038
100243003722500001200869295472510012101000010100006042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010306402162229629010000103003830038300383003830038
100243003722501001200103295472510010101000010100005042771601300183003730037282863287671001220100002010000300373003711100211091010100001000010006402165329631010000103003830038300383003830038
100243003722400001200103295472510010101000010100005042771601300183003730037282863287851001020100002010000300373003711100211091010100001000010306402162229629010000103003830038300383003830038
100243003722500001200103295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500001200441295472510010101000010100006042771601300183003730037282863287671001020100002010000300373003711100211091010100001000010026402162229629010000103003830038300383003830038
10024300372250000000103295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000010306408162229629210000103003830038300383003830038
100243003722500001200103295472510012101000012100006042771600300183003730037282863287671001020100002010000300373003721100211091010100001000010306422162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  scvtf v0.4s, v8.4s, #3
  scvtf v1.4s, v8.4s, #3
  scvtf v2.4s, v8.4s, #3
  scvtf v3.4s, v8.4s, #3
  scvtf v4.4s, v8.4s, #3
  scvtf v5.4s, v8.4s, #3
  scvtf v6.4s, v8.4s, #3
  scvtf v7.4s, v8.4s, #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)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)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601501272258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100031115135116020036800001002004020040200402004020040
80204200391501230258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100031115118016020036800001002004020040200402004020040
80204200391501272258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100031115118016020036800001002004020040200402004020040
80204200391501272258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100131115118016020036800001002004020040200402004020040
80204200391503972258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100031115118016020036800001002004020040200402004020040
80204200391506330258010810080008100800205006401321200202003920039997769990801202008003220080141200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391501272258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118016020036800001002004020040200402004020040
80204200391502772258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100131115118016020036800001002004020040200402004020040
80204200391501272258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100131115118016020036800001002004020040200402004020040
80204200391506072258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100101115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)9fa8acc5cfitlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500128225800101080000108000050640000120020200392003999943100198001020800002080000200392003911800211091010800001000050211141614162003680000102004020040200402004020040
8002420039150198225800101080000108000050640000120020200392003999943100198001020800002080000200392003911800211091010800001003050211171618162003680000102004020040200402004020040
800242003915012288225800101080000108000050640000120020200392003999943100198001020800002080000200392003911800211091010800001013050211161616172003680000102004020040200402004020040
80024200391501368225800101080000108000050640000020020200392003999923100198001020800002080000200392003911800211091010800001000050211161617162003680000102004020040200402004020040
800242003915010402580010108000010800005064000002002020039200399992310019804352080000208000020039200391180021109101080000100005021116169182003680000102004020040200402004020040
8002420039150104025800101080000108000050640000020020200392003999923100198001020800002080000200392003911800211091010800001000050211171617172003680000102004020040200402004020040
8002420039150139402580010108000010800005064000002002020039200399994310019800102080000208000020039200391180021109101080000100005021117168172003680000102004020040200402004020040
80024200391501042025800101080000108000050640000020020200392003999943100198001020800002080000200392003911800211091010800001000150211161616162003680000102004020040200402004020040
8002420039150104025800101080000108000050640000120020200392003999943100198001020800002080000200392003911800211091010800001000050211171610172003680000102004020040200402004020040
800242003915010402580010108000010800005064000012002020039200399994310019800102080000208000020039200391180021109101080000100005021181618132003680000102004020040200402004020040