Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTI (vector, 2S)

Test 1: uops

Code:

  frinti 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)0308191e3f4e51inst 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
10043037251006125472510001000100039816003018303730372414328951000100010003037303711100110000073416222629100030383038303830383038
100430372300126125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230106125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372300061254725100010001000398160030183037303724143289510001000100030373037111001100012173216222629100030383038303830383038
1004303724000103254725100010001000398160030183037303724143289510001000100030373037111001100012073216222629100030383038303830383038
10043037240006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinti 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)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037232000000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372320000000010329547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372320000000010329547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000371011611296330100001003003830038300383003830038
1020430037232000000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000000008229547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000001071011611296330100001003003830038300383003830038
1020430037232000000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037233000000006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000726295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000810100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
1002430037225000000107295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510034101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinti v0.2s, v8.2s
  frinti v1.2s, v8.2s
  frinti v2.2s, v8.2s
  frinti v3.2s, v8.2s
  frinti v4.2s, v8.2s
  frinti v5.2s, v8.2s
  frinti v6.2s, v8.2s
  frinti 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)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)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)9fa8acc5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039156213025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100101115118160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100031115118160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160020036800001002004020040200402004020040
802042003915603025801081008000810080020500640132200202003920039997769990801202008003220080032200392014911802011009910010080000100031115118160020036800001002004020040200402004020040
802042003915603025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160120036800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990802272008003820080038200482004811802011009910010080000100061115118160020036800001002004020040200402004020040
8020420039156123025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100001115118160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b191e3f51inst 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)9fa0a1a6a8acc2c5cfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500004025800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100000300502050618161662003680000102004020040200402004020040
80024200391560000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000050205016161662003680000102004020040200402004020040
800242003915500004025800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100000000502050116166162003680000102004020040200402004020040
800242003915500004025800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100000000502050116166162003680000102004020040200402004020040
800242003915500004025800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100000300502050111166162003680000102004020040200402004020040
800242003915500004025800101080000108000050640000152002020039200399996310019800102080000208000020039200391180021109101080000100000000502050212161662003680000102004020040200402004020040
800242003915600004025800101080000108000050640000102002020039200399996310019800102080000208000020039200391180021109101080000100000000502050113166162003680000102004020040200402004020040
80024200391550000402580010108000010800005064000015200202003920039999631001980010208000020800002003920039118002110910108000010000000050205015161662003680000102004020040200402004020040
8002420039155001040258001010800001080000506400001520020200392003999963100198001020800002080000200392003911800211091010800001000000005020500161616162003680000102004020040200402004020040
8002420039155000040258001010800001080000506400001520020200392003999963100198001020800002080000200392003911800211091010800001000000005020500161616162003680000102004020040200402004020040