Apple M1 Microarchitecture Research by Dougall Johnson

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

SADDLV (vector, 4H)

Test 1: uops

Code:

  saddlv s0, 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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  saddlv s0, 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)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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129547251010010010000100100005004277160053001830037300372826432874510100200100002002000030037300371110201100991001001000010000710511161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160053001830037300372826432874510100200100002002000030037300371110201100991001001000010000710001161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160003001830037300372826432874510100200100002002000030037300371110201100991001001000010000710001161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160003001830037300372826432874510100200100002002000030037300371110201100991001001000010000710511161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160003001830037300372826432874510100200100002002000030037300371110201100991001001000010010710001161129633100001003003830038300383003830038
1020430037225516129547991010010010000100100005004277160053001830037300372826482876310100200100002002000030037300371110201100991001001000010010710001161129633100001003003830038300383003830038
102043003722566129547251010010010000100100005004277160103001830037300372826432874510100200100002002000030037300371110201100991001001000010000710001161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160003001830037300372826432874510100200100002002000030037300372110201100991001001000010000710001161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160003001830037300372826432874510100200100002002000030037300371110201100991001001000010000710001161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160053001830037300372826432874510100200100002002000030037300371110201100991001001000010016710001161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b191e3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
10024300372240002761295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000021640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000640216232962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100020640216222962910000103003830038300383003830038
100243003722400006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722500006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000640216222962910000103003830038300383003830038
100243003722400006129547251001010100001010000504277160130018300373003728286328767100102010000202000030037300371110021109101010000100000663216222965310000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  saddlv s0, v8.4h
  saddlv s1, v8.4h
  saddlv s2, v8.4h
  saddlv s3, v8.4h
  saddlv s4, v8.4h
  saddlv s5, v8.4h
  saddlv s6, v8.4h
  saddlv s7, v8.4h
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151183161220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161220036800001002004020040200402004020040
802042003915005525801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151182162220036800001002004020040200402004020040
802042003915005325801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151182162220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151182162220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151182162220036800001002004020040200402004020040
8020420039150022025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151182162220036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001001011151182162220036800001002004020040200402004020040
802042003915033025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001001011151182161220036800001002004020040200402004020040
802042003915003525801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151182162120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b191e3f51inst 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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000040258001010800001080000506400001020020200392003999963100198001020800002016000020039200391180021109101080000100050200001016622003680000102004020040200402004020040
80024200391500006125800101080096108000050640000102002020039200399996710019800102080000201600002009920099118002110910108000010105020000316262003680000102004020040200402004020040
80024200391500004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010105020000216262003680000102004020040200402004020040
80024200391500004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010005020000616662003680000102004020040200402004020040
80024200391500008225800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010005020000216622003680000102004020040200402009120040
80024200391500004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010005020000616222003680000102004020040200402004020087
80024200391500004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010005020000616622003680000102004020040200402004020040
80024200391500004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010005020000216622003680000102004020040200402004020040
80024200391501004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010005020000216222003680000102004020040200402004020040
80024200391500004025800101080000108000050640000102002020039200399996310019800102080000201600002003920039118002110910108000010005020000216222003680000102004020040200402004020040