Apple M1 Microarchitecture Research by Dougall Johnson

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

UQXTN (4S)

Test 1: uops

Code:

  uqxtn v0.4h, 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)60696b6d6edispatch 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
100430372396125472510001000100039816013018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816013018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816013018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816003018030373037241532895100010001000303730371110011000073116112629100030383038303830383038
100430372236125472510001000100039816003018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816003018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816003018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816003018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372306125472510001000100039816003018030373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372206125472510001000100039816003018030373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  uqxtn v0.4h, 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)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)9fa8a9acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037225000128229547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722400006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003721102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723200006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100003007101161129633100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000001290061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000300061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000240061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000120061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372240000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  uqxtn v0.4h, v8.4s
  uqxtn v1.4h, v8.4s
  uqxtn v2.4h, v8.4s
  uqxtn v3.4h, v8.4s
  uqxtn v4.4h, v8.4s
  uqxtn v5.4h, v8.4s
  uqxtn v6.4h, v8.4s
  uqxtn v7.4h, 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)03181e1f3f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915000043425801081008000810080020500640132120020200392019399776999080120200800322008003220039200391180201100991001008000010000011151185220036800001002004020040200402004020040
802042003915000015825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620157800001002004020040200402004020040
802042003915000883025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
802042003915000030258010810080008100800205006401321200202003920039997711999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
802042003915000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100003111511828920036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020203952003999986999080120200800322008003220039200391180201100991001008000010000311151181620036800001002004020040200402004020040
8020420039150027030258010810080008100800205006409441200202003920039997711100158023420080136200801372011320096218020110099100100800001000247511151181620036800001002004020040200402004020040
802042003915001503025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
80204200391500603025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)9fa8a9acbranch mispredict (cb)cdcfd0d2icache miss (d3)d5d6d9dbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150004025800101080000108000050640000612002020039200399996310019800102080000208000020039200391180021109101080000100000050200004160043200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000512002020039200399996310019800102080000208000020039200391180021109101080000100000050200003160032200360080000102004020040200402004020040
8002420039150066125800101080000108000050640000612002020039200399996310019800102080000208000020039200391180021109101080000100000050200003160033200360080000102004020040200402004020040
800242003915001240258001010800001080000506400006120020200392003910005310019800102080000208000020039200391180021109101080000100000050200003160033200360080000102004020040200402004020040
80024200391500124025800101080000108000050640000612002020039200399996310019800102080000208000020039200391180021109101080000100000050200003160032200360080000102004020040200402004020040
80024200391500040258001010800001080000506400006120020200392003999963100198001020800002080000200392003911800211091010800001000000502000041600232003620080000102004020040200402004020040
8002420039150004025800101080000108000050640000612002020039200399996310019800102080000208000020039200391180021109101080000100000050200003160032200360080000102004020040200402004020040
8002420039150004025800101080000108000050640000612002020039200399996310019800102080000208000020039200391180021109101080000100000050200003160032200360080000102004020040200402004020040
80024200391500154025800101080000108000050640000712002020039200399996310019800102080000208000020039200391180021109101080000100000050200003160032200360080000102004020040200402004020040
80024200391500051525800101080000108000050640000712002020039200399996310019800102080000208000020039200391180021109101080000100000050200002160033200360080000102004020040200402004020040