Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (scalar, integer, D from D)

Test 1: uops

Code:

  scvtf d0, d0
  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)033f4e51inst 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)a0a6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073316222629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000373216222629100030383038303830863038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037226125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038
10043037236125472510001000100039816013018303730372414328951000100010003037303711100110000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf d0, d0
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225910132954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100055907101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722507262954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722502512954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722502512954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373008511102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000001032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010001306403162229629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001306402162229629010000103003830038300383003830038
100243003722500001201032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001306402162229629010000103003830038300383003830038
100243003722500001201032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001306402163229629010000103003830038300383003830038
100243003722500001201032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001306402162229629010000103003830038300383003830038
100243003722500001201032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001306402163329629010000103003830038300383003830038
10024300372250000001032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001306402162229629010000103003830038300383003830038
100243003722500001207262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010001306402162229629010000103003830038300383003830038
1002430037225000012046922948413410071131004815110506642852721302703032030357283162728897110322011139201032530371303208110021109101010000102011953327892642329860510000103031930369303693037330368
100243035622710779485284626294931351006314100561511050504277160030018300373003728286328767100102010000201000030037300371110021109101010000100021763328083812329880510000103041830367303703036630368

Test 3: throughput

Count: 8

Code:

  scvtf d0, d8
  scvtf d1, d8
  scvtf d2, d8
  scvtf d3, d8
  scvtf d4, d8
  scvtf d5, d8
  scvtf d6, d8
  scvtf d7, d8
  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)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)9fa8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150103025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402011220040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307081e1f3f51inst 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)9fa1a8acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020015161172003680000102004020040200402004020040
8002420039150001208225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001305020011169132003680000102004020040200402004020040
800242003915000008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001305020010161072003680000102004020040200402004020040
80024200391500012082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010013050201511161192003680000102004020040200402004020040
800242003915000120822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100130502018916992003680000102004020040200402004020040
80024200391500012082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010013050201571612112003680000102004020040200402004020040
8002420039150001208225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001005020156169112003680000102004020040200402004020040
800242003915000120822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502015111611102003680000102004020040200402004020040
800242003915000120402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100130502015101610102003680000102004020040200402004020040
800242003915000120822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100130502015111610112003680000102004020040200402004020040