Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMS (vector, 8H)

Test 1: uops

Code:

  fcvtms v0.8h, v0.8h
  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)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
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
100430372308525472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372606125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372308225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100530372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtms v0.8h, v0.8h
  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)0304080b18191e1f3f4e51inst 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)9fa1a6a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963300100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963300100001003003830038300383003830038
1020430037232000000061295472510100100100001001000050042771600300180300723003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963300100001003003830038300383003830038
10204300372330000012061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963300100001003003830038300383003830038
10204300372330000000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000000018891972329957400100001003056030375305543037430328
1020430276237011118795880756629547251010010010000100100005004277160030270030371301322828937288721131323111165220111593036730275911020110099100100100001002204218330710116112963301100001003003830038300383003830038
10204300372330000000251295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963300100001003003830038300383003830038
1020430037232000000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100001000710116112963300100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963300100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771600300180300373003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030809191e1f3f4e51inst 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
10024300372250201806129547251001010100001010000504277160130018300843008328292328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037224000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300853003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722400000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000037015006402162229629010000103003830038300383003830038
1002430037224000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000014529547441002110100001010000554277160130018300853013228286328767101612010000201000030037300371110021109101010000100600103206402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtms v0.8h, v8.8h
  fcvtms v1.8h, v8.8h
  fcvtms v2.8h, v8.8h
  fcvtms v3.8h, v8.8h
  fcvtms v4.8h, v8.8h
  fcvtms v5.8h, v8.8h
  fcvtms v6.8h, v8.8h
  fcvtms v7.8h, v8.8h
  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)03070a1e3f51inst 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
80204200491551003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010006111511811612200360800001002004020040200402004020040
802042003915513030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003921802011009910010080000100133111511821611200360800001002004020040200402004020040
80204200391551303025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010003111511811611200360800001002004020040200402004020040
80204200391551303025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811621201000800001002004020040200402004020040
80204200391561303025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010003111511811611200360800001002004020040200402004020040
802042003915513030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100196111511811611200361800001002004020040200402004020040
80204200391551103025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
80204200391551103025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
802042003915511030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100878111511811611200360800001002004020040200402004020040
80204200391551103025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010010111511811611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020216112003680000102004020040200402004020040
80024200391550040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010008705020116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010208705020116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010008405020116112003680000102004020040200402004020040
8002420039155003142580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100010805020116112003680000102004020040200402004020040
80025200391550040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010009305020116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010009005020116112003680000102004020040200402004020040
80024200391550040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010007805020116212003680000102004020040200402004020040
8002420039156004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000005020216222003680000102004020040200402004020040
800242003915500402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100010505020116112003680000102004020040200402004020040