Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTP (vector, 2S)

Test 1: uops

Code:

  frintp v0.2s, v0.2s
  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)03070a1e3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
10043037241102682547251000100010003981603018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037231102682547251000100010003981603018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
100430372411021102547251000100010003981603018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037231102682547251000100010003981603018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037231102682547251000100010003981603018303730372414328951000100010003037303711100110000377416442629100030383038303830383038
100430372311021102547251000100010003981603018303730372414328951000100010003037303711100110000377416442629100030383038303830383038
10043037241102682547251000100010003981603018303730372414328951000100010003037303711100110000377416442629100030383038303830383038
10043037231102682547251000100010003981603018303730372414328951000100010003037303711100110000377416442629100030383038303830383038
10043037241102682547251000100010003981603018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037241102682547251000100010003981603018303730372414328951000100010003037303711100110000077416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintp v0.2s, v0.2s
  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)03091e3a3f4e51inst 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)6061696b6d6edispatch 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)cdcfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330003122954725101001001000010010000500427716000300180300373003728271728740101002001000820010008300373003711102011009910010010000100001117170011611296450100001003003830038300383003830038
10204300372330001492954725101001001000010010000500427716000300180300373003728271728741101002001000820010008300373003711102011009910010010000100001117170012611296450100001003003830038300383003830038
1020430037233000682954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100030007100021622296330100001003003830038300383003830038
1020430037233000822954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100130007100021622296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100000007100021622296330100001003003830038300383003830038
1020430037232000612954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100000007100021622296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100000007100021622296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100000007100021622296330100001003003830038300383003830038
10204300372330120612954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100000007100021622296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716000300180300373003728264328745101002001000020010000300373003711102011009910010010000100000007100021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500001223295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006404162229629010000103003830038300383003830038
10024300372250000145295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372240000814295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000876295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001006006402242229629010000103003830038300383003830038
10024300372250000147295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000355295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001010006402162229629010000103003830038300383003830038
10024300372250000927295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000420295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000906295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
1002430037224000082295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintp v0.2s, v8.2s
  frintp v1.2s, v8.2s
  frintp v2.2s, v8.2s
  frintp v3.2s, v8.2s
  frintp v4.2s, v8.2s
  frintp v5.2s, v8.2s
  frintp v6.2s, v8.2s
  frintp v7.2s, v8.2s
  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)0307080a0b181e3f51inst 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)9fa8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003915511102030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915510100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915510100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
8020420039155101000600258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915510100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003921802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915610100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915510100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181162120036800001002004020040200402004020040
802042003915510100030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181161120036800001002004020040200402004020040
802042003915510100030258010810080008100800205006401320200202009920039997769990801202008003220080032200392003951802011009910010080000100000011151181161220036800001002004020040200402004020040
8020420039155000000505258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151182161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f243a3f51inst 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)9fa1a8accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051155000044325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050203160322003680000102004020040200402007720040
800242003915600006325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050203160312003680000102004020040200402004020040
800242003915500008225800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050204160612003680000102004020040200402004020040
800242003915600004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050202160312003680000102004020040200402004020040
800242003915600004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001007050203160312003680000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001050203160512003680000102004020040200402004020040
800242003915500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000050203160312003680000102004020040200402004020040
800242003915500006325800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050203160212003680000102004020040200402004020040
8002420039156000040258001010800001080000506400000200202003920039999631100198001020800002080000200392003911800211091010800001000050205160322003680000102004020040200402004020040
800242003915500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000050204160522003680000102004020040200402004020040