Apple M1 Microarchitecture Research by Dougall Johnson

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

SMAXV (vector, 4H)

Test 1: uops

Code:

  smaxv 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)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
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000373116112629100030383038303830383038
100430372302142547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  smaxv 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)031e1f3a3f4e51inst 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
10204300372250006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160130018300373003728264328745101002001017520020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100037103161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000997101161129633100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010001717101161129633100001003003830038300383003830038
10204300372250002122954725101001001000810010000500427716003001830037300372826432874510100200100002002000030084300371110201100991001001000010001147101161129633100001003003830038300383003830038
10204300372240006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100037101161129633100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010001777101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010001177101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b18191e1f3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000306404165529629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006696166829629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000006404166429629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000202000030037300371110021109101010000100037006405165529629010000103003830038300383003830038
100243003722500000061295472510010101000012100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000411106405165429629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018301793003728286328767100102010000202000030037300371110021109101010000100228833006406166629629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010004006404165629629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010004006406165629629010000103003830038300383003830038
100243003722400000010322954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010004007085165629629010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010006606405166629629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  smaxv h0, v8.4h
  smaxv h1, v8.4h
  smaxv h2, v8.4h
  smaxv h3, v8.4h
  smaxv h4, v8.4h
  smaxv h5, v8.4h
  smaxv h6, v8.4h
  smaxv 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): 0.2505

retire (01)cycle (02)0309191e1f3f51inst 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)9fa1a8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601500000302580108100800081008023650064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100001231115154016020036800001002004020040200402004020148
8020420039156001203025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000031115118016020036800001002004020040200402004020040
802042003915000007225801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020200392014199776999080120200800322001600642003920039118020110099100100800001000061115118016020036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401320200202003920039997769990801202008003220016006420039200391180201100991001008000010003201115118016020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000031115118016020036800001002004020040200402004020040
8020420039150011203025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000101115118016020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
8020420039150000030258010810080112100800205006401321200202003920039997769990801202008003220016006420039200394180201100991001008000010000451115118016020158800001002004020040200402004020040
8020420039150001203025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001009031115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020000516000462003602180000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001004505020000516000532003601580000102004020040200402004020040
8002420039150000402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010015050200005160001062003601580000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020000316000352003601480000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020801402016000020039200391180021109101080000100015020000516000542003601580000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001005105020000516000532003601480000102004020040200402004020040
800242003915000092225800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100005020000616000532003602680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000103005020000316000352003602180000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001004505020000316000552003601980000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100005020000716000452003601380000102004020040200402004020040