Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHRN (S)

Test 1: uops

Code:

  sqshrn h0, s0, #3
  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
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303722636125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000373216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqshrn h0, s0, #3
  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)03080918191e1f3f4e51inst 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)9fa0a8a9accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204304662281099933772584929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
1020430037225000327906129547251010010010000100101506304282568130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300703003711102011009910010010000100000071001161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
102043003722500002406129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
10205300372250000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
102043003722500001208229547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
10204300372240000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000552571001161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000012006129547251001010100001010000504277160130018300373003728286328803100102010000201000030037300371110021109101010000100000000006402162229667010000103003830038300383003830038
1002430037225000006006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402161229629010000103003830038300383003830038
1002430037225000000015853294661711009619100641711500874288833130342304643027428322422888011513221146022114843022430498101100211091010100001024012278754008344975630007210000103051430555305073046230512
100243041422801000240010329466153100701110008181090076428632213030630415304042831117289151106622106622411302304143045081100211091010100001022212250930008372888329973410000103055830461305123050830464
10024305102281011010124288007342954742100371510000121015050427716003001830037303202831437288971031020109812411306304163013381100211091010100001020412233530008354985629989610000103055630506303943051130511
100243050722911049190210560655929448246100921710080161155750427716003012630415301782829382876710010201000020106573027530037111002110910101000010002042515340089751215630100310000103055730651306533065030643
100243046323801113141716114406582294481531006818100331211200604283920130018300373003728286328767100102010000201000030037300371110021109101010000100002000006402232229629010000103003830038300383003830038
1002430037224000000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037224000000006129547251001910100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
1002430037224000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000030006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqshrn h0, s8, #3
  sqshrn h1, s8, #3
  sqshrn h2, s8, #3
  sqshrn h3, s8, #3
  sqshrn h4, s8, #3
  sqshrn h5, s8, #3
  sqshrn h6, s8, #3
  sqshrn h7, s8, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)9fa0a1a7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151183160020036800001002004020040200402004020040
80204200391500000090069525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500000018003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039150000003003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039150000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039155000000008725801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039150000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160120036800001002004020040200402004020040
802042003915000000492003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039150000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500000021003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b191e3f51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015000246125800101080097108000050640000212002020039200399996310019800102080000208000020039200391180021109101080000100305020616432003680000102004020040200402004020040
80024200391500004025800101080000108000050640000602002020039200399996310019800102080000208000020039200391180021109101080000100005020416432003680000102004020040200402004020040
80024200391500004025800101080000108000050640000402002020039200399996310019800102080000208000020039200391180021109101080000100005020416432003680000102004020040200402004020040
80024200391500004025800101080000108000050640000402002020039200399996310019800102080000208000020039200391180021109101080000100005020316342003680000102004020040200402004020040
80024200391500004025800101080000108000050640000402002020039200399996310019800102080000208000020039200391180021109101080000100005020416432003680000102004020040200402004020040
800242003915000013525800101080000108000050640000402002020039200399996310019800102080000208000020039200391180021109101080000100005020316442003680000102004020040200402004020040
80024200391500004025800101080000108000050640000412002020039200399996310019800102080000208000020039200391180021109101080000100005020416442003680000102004020040200402004020040
80024200391500004025800101080000108000050640000402002020039200399996310019800102080000208000020039200391180021109101080000100005020416432003680000102004020040200402004020040
80024200391500004025800101080000108000050640000402002020039200399996310019800102080000208000020039200391180021109101080000100005020316342003680000102004020040200402004020040
8002420039150000204225800101080000108000050640000412002020039200399996310019800102080000208000020039200391180021109101080000100005020416342003680000102004020040200402004020040