Apple M1 Microarchitecture Research by Dougall Johnson

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

FMINNMV (4H)

Test 1: uops

Code:

  fminnmv h0, v0.4h
  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)03070a3a3f4e51inst 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)a0a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723112722547251000100010003981603018303730372414328951000100010003037303711100110000010077416442629100030383038303830383038
1004303723112672547251000100010003981603018303730372414328951000100010003037303711100110000000077416442629100030383038303830383038
1004303723112672547251000100010003981603018303730372414328951000100010003037303711100110000000377416442629100030383038303830383038
1004303722112682547251000100010003981603018303730372414328951000100010003037303711100110000000077416442629100030383038303830383038
1004303723112682547251000100010003981603018303730372414328951000100010003037303711100110000000077416442629100030383038303830383038
1004303723112682547251000100010003981603018303730372414328951000100010003037303711100110000000077416442629100030383038303830383038
1004303723112672547251000100010003981603018303730372414328951000100010003037303711100110000000077416442629100030383038303830383038
1004303722112682547251000100010003981603018303730372414328951000100010003037303711100110000000377416442629100030383038303830383038
1004303723112682547251000100010003981603018303730372414328951000100010003037303711100110000000677416442629100030383038303830383038
1004303723112682547251000100010003981603018303730372414328951000100010003037303711100110000000677416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  fminnmv h0, v0.4h
  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)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071021622296330100001003003830038300383003830038
102043003722500577429547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071021622296330100001003003830038300383003830038
10204300372250012729547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001622296330100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071021622296330100001003003830038300383003830038
10204300372250037929547251010012010016110100005004277160030018300373003728264728745101002001000020010000300373003731102011009910010010000100000071021622296330100001003003830038300383003830038
10204300372250014529547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071021622296330100001003003830038300383003830038
102043003722400395129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071021622296330100001003003830038300383003830038
10204300372250010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100160071021622296330100001003003830038300383003830038
10204300372250310329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071021622296330100001003003830038300383003830038
10204300372250012429547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000050329547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722400000014529547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000012429547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000010129547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000014729547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383008230038
100243003722500000012429547251001010100001010000504277160130065030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500009012429547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000012429547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000010329538251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000014729547251001010100001010000504277160130018030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fminnmv h0, v8.4h
  fminnmv h1, v8.4h
  fminnmv h2, v8.4h
  fminnmv h3, v8.4h
  fminnmv h4, v8.4h
  fminnmv h5, v8.4h
  fminnmv h6, v8.4h
  fminnmv h7, v8.4h
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)031e1f3f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150007225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010010011151180160020036800001002004020040200402004020040
8020420039150007425801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391506074925801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002005020049200492004920050
8020420049150008527801161008001610080028500640196120029200482004899769998680128200800382008003820049200481180201100991001008000010000022251281231120046800001002004920049200492004920050
8020420048150006427801161008001610080028500640196120029200492004899769998680128200800382008003820049200491180201100991001008000010000022251291231120046800001002005020050200492004920049
8020420048150006426801161008001610080028500640196120029200482004999769998680128200800382008003820049200481180201100991001008000010000022251281231220045800001002004920050200502004920050
802042004915600173268011610080016100800285006401961200292004920110997610998680128200800382008003820049200481180201100991001008000010000022251291231120045800001002005020049200492004920050
8020420048150006426801161008001610080028500640196120029200492004999769998680128200800382008003820048200481180201100991001008000010010022251291231120046800001002005020259200492005020049
8020420048150008527801161008001610080028500640196120029200482004899769998680128200800382008003820048200481180201100991001008000010000022251281231120045800001002004920050200502005020049

1000 unrolls and 10 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)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)9fa8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115001262580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050202162520036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050202162420036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050202162520036080000102004020040200402004020040
800242003915001032580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050202162520036080000102004020040200402004020040
800242003915001912580010108008010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050202162520036080000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050202162520036080000102004020040200402004020040
800242003915005632580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050202162420036080000102004020040200402004020040
80024200391500402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100150202162320036080000102004020040200402004020040
80024200391500822580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050202162420036080000102004020040200402004020040
800242003915001472580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050202162220036080000102004020040200402004220040