Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLV (vector, 16B)

Test 1: uops

Code:

  uaddlv h0, v0.16b
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372315612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000673116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uaddlv h0, v0.16b
  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)031e1f3f4e51inst 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
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250014729547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830084
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0309181e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830321300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010007101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000842954743100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
1002430037225000612954725100101010024101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000682216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uaddlv h0, v8.16b
  uaddlv h1, v8.16b
  uaddlv h2, v8.16b
  uaddlv h3, v8.16b
  uaddlv h4, v8.16b
  uaddlv h5, v8.16b
  uaddlv h6, v8.16b
  uaddlv h7, v8.16b
  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)03071e3f51inst 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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
8020420039150103025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500022025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151370160020036800001002004020040200402004020040
8020420039150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

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)5f6061696d6edispatch 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)9fa1a8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150082258001010800001080000506400000002002020039200399996310019800102080000201600002003920039118002110910108000010001505020000416342003680000102004020040200402004020040
800242003915004025800101080000108000050640000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020000216422003680000102004020040200402004020040
800242003915004025800101080000108000050640000015200202003920039999631001980010208000020160000200392003911800211091010800001001005020000416242003680000102004020040200402004020040
800242003915004025800101080000108000050640000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020500416242003680000102004020040200402004020040
800242003915004025800101080000108000050640000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020510216242003680000102004020040200402004020040
800242003915004025800101080000108000050640756015200202003920039999631001980010208000020160000200392003911800211091010800001000005020510216742003680000102004020040200402004020040
800242003915004025800101080000108000050640000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020510216622003680000102004020040200402004020040
800242003915004025800101080000108000050640000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020000416642003680000102004020040200402004020040
800242003915004025800101080000108000050640000015200202003920039999631001980010208000020160000200392003911800211091010800001000005020000316242003680000102004020040200402004020040
800242003915004025800101080000108000050640000000200202003920039999631001980010208000020160000200392003911800211091010800001000005020500416442003680000102004020040200402004020040