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, 16B)

Test 1: uops

Code:

  saddlv 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)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
100430372306125472510001000100039816013018303730372414328951000100020003037303711100110000073216112629100030383038303830383038
1004303723156125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073124112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001008100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  saddlv 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)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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000407101161129633100001003003830038300383003830038
10204300372250612954725101411001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010022607101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000207101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826432874510100200100002002000030037300371110201100991001001000010000207101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000207101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000007101241129633100001003003830038300383003830038
10204300372250612954798101001001000010010150500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000207101161129633100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000207101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000207101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002002000030037300371110201100991001001000010000507101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e1f3a3f4e51inst 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)72scheduler 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
10024300372250002622954725100101010000101000050427716013001803003730037282867328767100102010000202000030037300371110021109101010000100064481610102962910000103003830038300383003830038
10024300372250002622954725100101010000101000050427716003001833003730037282860328767100102010000202000030037300371110021109101010000101064410161052962910000103003830038300383003830038
1002430037225000262295471011001010100001010000504277160130018030037300372828601128786100102010000202000030037300371110021109101010000100064452410102962910000103003830038300383003830038
100243003722500026229547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001030644101610102962910000103003830038300383003830038
100243003722500026229547251001010100001010000504277160030018030037300372828603287671001020100002020000300373003711100211091010100001000644101610102962910000103003830038300383003830038
100243003722500026229547251001010100001010000504277160030018030037300372828603287671001020100002020000300373003711100211091010100001020644101710102962910000103003830038300383003830038
10024300372250002622954725100101010000101000050427716013001803003730037282860328767100102010000202000030037300371110021109101010000103064410165102962910000103003830038300383003830038
100243003722500026229547961001011100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000644101610102962910000103003830038300383003830038
100243003722500026229547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001013644101610102962910000103003830038300383003830038
100243003722500026229547251001010100001010000504277160130018030037300372828603287671001020100002020000300373003711100211091010100001000644101610102962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  saddlv h0, v8.16b
  saddlv h1, v8.16b
  saddlv h2, v8.16b
  saddlv h3, v8.16b
  saddlv h4, v8.16b
  saddlv h5, v8.16b
  saddlv h6, v8.16b
  saddlv 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)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
8020420039150060025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200801362001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915103025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001001011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000311151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3a3f51inst 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)9fa8accfd0d2d5d6dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500024125800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010005024001516001316200360080000102004020040200402004020040
800242003915000241258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000100050240016160015142003620080000102004020040200402004020040
80024200391500024125800101080000108000050640000020020320039200399996310019800102080000201600002003920039118002110910108000010305024001416001616200360080000102004020040200402004020040
8002420039150002632580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001000502400916001316200360080000102004020040200402004020040
800242003915000241258001010800001080000506400001200200200392003999963100198001020800002016000020039200391180021109101080000103605024001416001715200360080000102004020040200402004020040
80024200391500024125800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010005024001616101616200360080000102004020040200402004020040
80024200391500024125800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010005024001616001516200360080000102004020040200912004020040
8002420039150002412580010108000010800005064000002002002003920039999631001980010208000020160000200392003911800211091010800001037105502400151600169200360080000102004020040200402004020040
80024200391500024125800101080000108000050640000020020020039200399996310019800102080000201600002003920039118002110910108000010005024001616001917200360080000102004020040200402004020040
800242003915000241258001010800001080000506400000200200200392003999963100198001020800002016000020039200391180021109101080000105335024001516001512200360080000102004020040200402004020040