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, 4S)

Test 1: uops

Code:

  frinti v0.4s, v0.4s
  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)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)a0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000010073324222664100030383038303830383038
1004303723661254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000003073216222629100030383038303830383038
1004303724661254725100010001000398160301830373037241432895100010001000308330371110011000000073216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000200273216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038
10043037241261254725100010001000398160301830373037241432895100010001000303730371110011000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinti v0.4s, v0.4s
  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)030a1e3f4e51inst 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)9fa1a6a8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372330094295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000020007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771600300183003730037282643287651010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
102043003723201561295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000307101161129633100001003003830038300383003830038
10204300372320061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038
10204300372320661295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000307101161129633100001003003830038300383003830038
10204300372330061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243068924411414196288084482943715310100181008812107507142906800300183008430037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372320000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372320003061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001010640224222962910000103003830038300383003830038
10024300372330000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinti v0.4s, v8.4s
  frinti v1.4s, v8.4s
  frinti v2.4s, v8.4s
  frinti v3.4s, v8.4s
  frinti v4.4s, v8.4s
  frinti v5.4s, v8.4s
  frinti v6.4s, v8.4s
  frinti v7.4s, v8.4s
  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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
802042003915563025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160201590800001002004020040200402004020040
8020420039155050525801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
802042003915503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040
8020420039155011425801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100005311151180160200360800001002004020040200402004020040
8020420039155123025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020616662003680000102004020040200402004020040
800242003916100402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020616652003680000102004020040200402004020040
800242003915600402580010108000010800005064000012002020039200399996710019800102080000208000020039200391180021109101080000100005020516662003680000102004020040200402004020040
8002420039156004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001042005020516562003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020516542003680000102004020040200402004020040
8002420039155003252580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020416662003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020416542003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020516562003680000102004020040200402004020040
800242003915500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020516562003680000102004020040200402004020040
800242003915600402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100005020616752003680000102004020040200402004020040