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, 8H)

Test 1: uops

Code:

  saddlv s0, v0.8h
  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)03181e3f4e51inst 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
1004303722006125472510001000100039816013018303730372414328951000100020003037303711100110000373116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722106125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220012325472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
10043037220010325472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  saddlv s0, v0.8h
  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)03081e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295472510100100100001001000050042771600300183003730037282717287411010020010008200200163003730037111020110099100100100001000011171711600296460100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282716287411010020010008200200163003730037111020110099100100100001000011171801600296450100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771600300183003730037282873287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722400251295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000291300071011611296330100001003003830038300383003830038
102043003722500536295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500536295472510100100100001001000050042771600300183003730037282643287451010020010180200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
102043003722500536295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011610296330100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011711296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000008229547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500001506129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372300000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  saddlv s0, v8.8h
  saddlv s1, v8.8h
  saddlv s2, v8.8h
  saddlv s3, v8.8h
  saddlv s4, v8.8h
  saddlv s5, v8.8h
  saddlv s6, v8.8h
  saddlv s7, v8.8h
  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)03191e3a3f51inst 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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151181160020036800001002004020040200402004020040
802042003915000036925801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010040000011151180160020036800001002004020040200402004020040
802042003915000012525801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008031010080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500005325801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915005703025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3a3f51inst 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)9fa0a1a8accfd2d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500002412580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100000502472016151720036080000102004020040200402004020040
8002420039150000262258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010000050246716151620036080000102004020040200402004020040
800242003915000021712580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100000502411216141620036080000102004020040200402004020040
80024200391500002412580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100000502401416151520036080000102004020040200402004020040
8002420039150000241258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010000050240816141620036080000102004020040200402004020040
8002420039150000241258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010000050240161681520036080000102004020040200402004020040
80024200391500002412580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100000502401716171620036080000102004020040200402004020040
8002420039150000262258001010800001080000506400002002020039200399996310019800102080000201600002003920039118002110910108000010000050240161681520036080000102004020040200402004020040
80024200391500002412580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100000502401616141620036080000102004020040200402004020040
80024200391500002562580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100000502401416161420036080000102004020040200402004020040