Apple M1 Microarchitecture Research by Dougall Johnson

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

UABD (vector, 4H)

Test 1: uops

Code:

  uabd v0.4h, v0.4h, v1.4h
  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)031e3f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
10043037236061254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
10043037236361254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
100430372211161254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
1004303723961254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100073116112630100030383038303830383038
1004303723061254825100010001000398313130183037308524153289510001000200030373037111001100073116112630100030383038303830383038
10043037236061254825100010001000398313130183037303724153289510001000200030373037111001100073116122630100030383038303830383038

Test 2: Latency 1->2

Code:

  uabd v0.4h, v0.4h, v1.4h
  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)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)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)9fa6a8acc2c5cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372252161295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007100011611296340100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100003007100011611296340100001003003830038300383003830038
1020430037225661295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007100011611296340100001003003830038300383003830038
102043003722527612954825101001001000010010000500427731310300183003730037282652128745101002001000020020000300373003711102011009910010010000100000007100021611296340100001003003830038300383003830038
102043003722548061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007100011611296340100001003003830038300383003830038
10204300372251561295482510100100100001001000050042773131030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007105511611296340100001003003830038300383003830038
102043003722536661295482510100100100001001000050042773130530018300373003728265328745101002001000020020000300373003711102011009910010010000100000007100011611296340100001003003830038300383003830038
10204300372242761295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007100011611296340100001003003830038300383003830038
102043003722541761295482510100100100001001000050042773131030018300373003728265728764101002001000020020000300373003711102011009910010010000100000007105511611296340100001003003830038300383003830038
10204300372253961295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007105511611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0304090b18191e1f3a3f4e51inst 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
100243003722500000900262295392510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006441016101029630010000103003830038300383003830038
1002430037225000000026229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000644111611529630010000103003830038300383003830038
1002430037224000000026229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000644616111129630010000103003830038300383003830038
10024300372250000012026229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000644816101029630010000103003830038300383003830038
10024300372250000015026229548251001010100001010000504277313030018300373003728287328767101602010000202000030037300371110021109101010000100000000644101611529630010000103003830038300383003830038
1002430037225000001950262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006441016101129630010000103003830038300383003830038
1002430037225000000026229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000644101651029630010000103003830038300383003830038
1002430037225000000026229548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000000644516101029630010000103003830038300383003830038
10024300372250000000262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006441116101029630010000103003830038300383003830038
1002430037224000000026229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000000644101681029630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uabd v0.4h, v1.4h, 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)03080b1e3f4e51inst 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)9fa0a8cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250027361295482510100100100001001000050042773131230018300373003728265328745101002001000020020000300373003711102011009910010010000100007102221622296340100001003003830038300383003830038
1020430037225002761295482510100100100001001000050042773131230018300373003728265328745101002001000020020000300373003711102021009910010010000100007100021622296340100001003003830038300383003830038
1020430037225000726295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100007100021622296340100001003003830038300383003830038
102043003722501061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100007100021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130030018300373003728265328745101002001000020020000300373003711102011009910010010000100007100021622296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130030018300373003728277328763101002001000020020000300373003711102011009910010010000100017102021622296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731312300183003730181282752128745104552021050221420992301803003731102011009910010010000100007102021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131230018300373003728265328745101002001000020020000300373003711102011009910010010000100007102021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131230018300373003728265328745101002001000020020000300373003711102011009910010010000100007102021622296340100001003003830038300383003830038
1020430037224001261295482510100100100001001000050042773131230018300373003728265328745101002001000020020000300373003711102011009910010010000100007102021622296340100001003003830038300383003830038

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)9fa0a1accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722557612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372253612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640224222963010000103003830038300383003830038
1002430037225242292954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722518842954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640217222963010000103003830038300383003830038
10024300372259612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722518612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640316222963010000103003830038300383003830038
100243003722515612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722521612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722512612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uabd v0.4h, v8.4h, v9.4h
  uabd v1.4h, v8.4h, v9.4h
  uabd v2.4h, v8.4h, v9.4h
  uabd v3.4h, v8.4h, v9.4h
  uabd v4.4h, v8.4h, v9.4h
  uabd v5.4h, v8.4h, v9.4h
  uabd v6.4h, v8.4h, v9.4h
  uabd v7.4h, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491509412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051102161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915004125801001008000010080000500640000120020200392003999731799978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
8020420039150378412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915024412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051331161120036800001002004020040200402004020040
80204200391500412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915094125801001008000010080000500640000120020200392003999733100778010020080000202160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915012412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915002312580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150540402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020516432003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416432003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416432003680000102004020040200402004020040
800242003915000612580010108000010800005064000012002020039200399996310019800102080000201600002008920090118002110910108000010005020316432003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416342003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416342003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416432003680000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100245020416432003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020145200399996310019800102080000201600002003920039118002110910108000010005020416342003680000102004020040200402004020040
800242003915000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020416342003680000102004020040200402004020040