Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTZ (scalar, H)

Test 1: uops

Code:

  frintz h0, h0
  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)03191e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300822547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612538251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372200612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110004273116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372300612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintz h0, h0
  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)033f4e51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372256129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101162129633100001003003830038300383003830038
10204300372256129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372256129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372256129547431010010010000100100005004277160130018300373003728264328745101002001000020010000300373013511102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722572629529251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722461295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000007207101161129633100001003003830038300383003830038
10204300372246129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372246129547251010010010000100100005004277160130018300373003728264328745101002001016620010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372256129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372256129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225126129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100030640216222962910000103003830038300383003830038
10024300372251210329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100130640216222962910000103003830038300383003830038
10024300372251210329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100130640216222962910000103003830038300383003830038
1002430037225126129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100130640216222962910000103003830038300383003830038
10024300372241210329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640216222962910000103003830038300383003830038
1002430037225127262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010032220640216222962910000103003830038300383003830038
10024300372251210329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100130640216222962910000103003830038300383003830038
1002430037225126129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100030640216222962910000103003830038300383003830038
10024300372251210329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100130640216222962910000103003830038300383003830038
10024300372251210329547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100100640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintz h0, h8
  frintz h1, h8
  frintz h2, h8
  frintz h3, h8
  frintz h4, h8
  frintz h5, h8
  frintz h6, h8
  frintz h7, h8
  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)03073f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815023025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181160120036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180161020036800001002004020040200402004020040
802042003915005325801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010003011151180161020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150013925801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915005125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915007225801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180161020036800001002004020040200402004020040
8020420039149044525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180161020036800001002004020040200402004020040
8020420039150033825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e1f3f51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150012014925800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001013050202161362003680000102004020040200402004020040
80024200391500120822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101305020316832003680000102004020040200402004020040
80024200391500008625800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001013050203161072003680000102004020040200402004020040
800242003915001201702580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020416962003680000102004020040200402004020040
800242003915001205782580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101305020416372008680000102004020040200402004020040
80024200391500003892580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020416542003680000102004020040200402004020040
800242003915001201452580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101005020416642003680000102004020040200402004020040
800242003915001201452580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101005020416462003680000102004020040200402004020040
800242003915001201912580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101305020416642003680000102004020040200402004020040
800242003915001201872580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100305020416722003680000102004020040200402004020040