Apple M1 Microarchitecture Research by Dougall Johnson

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

ADDV (4S)

Test 1: uops

Code:

  addv s0, v0.4s
  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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
100430372307882547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037220612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037230612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
100430372312612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037220612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037233612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037230612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037223612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038
10043037239612547251000100010003981601301830373037241432895100010002000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  addv s0, v0.4s
  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)0308191e1f3a3f4e51inst 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)9fa1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000002292954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
10204300372250036001282952925101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722400000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722400000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716013001803003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
102043003722500000612954725101001001000010010000500427716013006603003730037282643287451010020010000200200003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038

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)696b6d6edispatch 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
100243003722406129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640316222962910000103003830038300383003830038
100243003722506129547251001010100001010000554277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243008422506129547251001010100001010000504277160300180300373003728286328767100102010000202000030037300371110021109101010000100640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  addv s0, v8.4s
  addv s1, v8.4s
  addv s2, v8.4s
  addv s3, v8.4s
  addv s4, v8.4s
  addv s5, v8.4s
  addv s6, v8.4s
  addv s7, v8.4s
  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)696d6edispatch 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)9fa8c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150633025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
80204200391504653025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039150060025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039150665125801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
8020420039150213025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010001115118016020036800001002004020040200402004020040

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)5f60696d6edispatch 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)9fa0a1a8c2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000005020000121600022200360080000102004020040200402004020040
80024200391492740258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000502000021600022200360080000102004020040200402004020040
800242003915027705258001010800001080000506400001120020200392003999963100198001020800002016000020039200391180021109101080000100000502000021600062200360080000102004020040200402004020040
80024200391504540258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000502000021600026200360080000102004020040200402004020040
8002420039150040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000502000061600022200360080000102004020040200402004020040
80024200391504540258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000502000021600022200360080000102004020040200402004020040
80024200391502140258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000502000061600062200360680000102004020040200402004020040
8002420039150040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000502000021600122200360080000102004020040200402004020040
80024200391503940258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100000502001021600022200860080000102004020040200402004020040
8002420039149040258001010800001080000506400000120020200392003999963100198001020800002016000020039200391180021109101080000100010502000021600026200360080000102004020040200402004020040