Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHRN2 (4S)

Test 1: uops

Code:

  sqshrn2 v0.8h, v1.4s, #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
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110007073216222630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100001273216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372308225482510001000100039831303018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
1004303723126125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqshrn2 v0.8h, v1.4s, #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)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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225017529548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100010071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225014529548251010010010000100100005004277313130018300853003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240021029548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006403162229630010000103003830038300383003830038
1002530037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250016629548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402163229630010000103008630168300383003830038
1002430133225106129548251001010100001010000504277313130018300373003728287328767100102010000202000030084300371110021109101010000101006402162229630010000103003830038300383003830038
10024300372250021229548451001910100001010149604277313130018300373003728290828767100102010329202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000126402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqshrn2 v0.8h, v0.4s, #3
  movi v0.16b, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722561295472510100100100001001000050042771601300180300373003728271628741101002001000820020016300373003711102011009910010010000100001117181629645100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300180300373003728271628740101002001000820020000300373003711102011009910010010000100001117181629645100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300180300373003728271628740101002001000820020016300373003711102011009910010010000100001117181629645100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300180300373003728271728741101002001000820020016300373003711102011009910010010000100001117171629646100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300180300373003728271628740101002001000820020016300373003711102011009910010010000100001117171629646100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300180300373003728271628741101002001000820020016300373003711102011009910010010000100001117181630034100001003003830038300383003830038
102043003722561295472510100100100001001000050042771601300180300373003728271628741101002001000820020016300373003711102011009910010010000100001117181629645100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300180300373003728271728741101002001000820020016300373003711102011009910010010000100001117171629645100001003003830038300383003830038
102043003722461295472510100100100001001000050042771600300180300373003728271628741101002021000820020016300373003711102011009910010010000100001117181629645100001003003830038300383003830038
102043003722561295472510100100100001001000050042771600300180300373003728271728740101002001000820020016300373003711102011009910010010000100001117181629645100001003003830038300383003830038

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)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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
10024300372240612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
10024300372240612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722509952954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640316362962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038
100243003722401452954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000640316332962910000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqshrn2 v0.8h, v8.4s, #3
  movi v1.16b, 0
  sqshrn2 v1.8h, v8.4s, #3
  movi v2.16b, 0
  sqshrn2 v2.8h, v8.4s, #3
  movi v3.16b, 0
  sqshrn2 v3.8h, v8.4s, #3
  movi v4.16b, 0
  sqshrn2 v4.8h, v8.4s, #3
  movi v5.16b, 0
  sqshrn2 v5.8h, v8.4s, #3
  movi v6.16b, 0
  sqshrn2 v6.8h, v8.4s, #3
  movi v7.16b, 0
  sqshrn2 v7.8h, v8.4s, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

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)60696d6escheduler 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)9fa0a1a7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891511529258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011911600200621600001002006620066200662006620066
1602042006515090124258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111012001600200621600001002006620066200662006620066
160204200651509329258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901611200621600001002006620066200662006620066
160204200651518429258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
160204200651517529258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111012011610200621600001002006620066200662006620066
16020420065150426504258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111012011611200621600001002006620066200662006620066
160204200651501022925801161008001610080028500640196120045200652006561280128200800282001600562006520065111602011009910010016000010000004931111012011611200621600001002006620066200662006620066
160204200651509029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
16020420065150029258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901600200621600001002006620066200662006620066
160204200651519929258011610080016100800285006401961200452006520065612801282008002820016005620065200651116020110099100100160000100000001111011901610200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b191e1f3f51inst 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)5f6061696d6escheduler 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)9fa0a6a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242008615000100516680010108000010800005064000011520029200502004632280114208000020160210200522005011160021109101016000010000001004413322414431115182004930160000102004720047200532005320047
1600242004815000092645164800101080000108000050640832011020031200502005032280010208000020160000200622004611160021109101016000010020001004213511917342219222004930160000102005120053200532005320051
16002420050150000004525800101080000108000050640000011020033200502005032280010208000020160000200462005011160021109101016000010000001004413512117941219202004915160000102004720051200492005320051
16002420052150000004525800101080104108000050640000111020027200462004832280010208000020160000200502004611160021109101016000010000001004213512016321117182004315160000102004920047200472004920049
16002420048150000004525800101080000108000050640000111020029200462004832280010208000020160000200522004611160021109101016000010000001004213511914121119182004315160000102004720047200492004920049
16002420048150000004525800101080000108000050640000111020027200482004632280010208000020160000200462004611160021109101016000010000001003613511813921120202004515160000102004920049200492004720049
16002420046150000004525800101080000108000050640000111020027200462004632280010208000020160000200522004611160021109101016000010000001004013511813921116182004316160000102004920047200472004920047
16002420048150000004525800101080000108000050640000111020027200462004632280010208000020160000200462004611160021109101016000010000001004313511814721119182004515160000102004720047200472004720049
16002420046150000004525800101080000108000050640000111020029200462004632280010208000020160000200532004611160021109101016000010000001004113511914221118172004316160000102004720047200472004720049
16002420046150000004525800101080000108000050640000111020027200462004632280010208000020160000200502004611160021109101016000010000001004113511313621113152004715160000102004720047200472004720047

Test 5: throughput

Count: 16

Code:

  sqshrn2 v0.8h, v16.4s, #3
  sqshrn2 v1.8h, v16.4s, #3
  sqshrn2 v2.8h, v16.4s, #3
  sqshrn2 v3.8h, v16.4s, #3
  sqshrn2 v4.8h, v16.4s, #3
  sqshrn2 v5.8h, v16.4s, #3
  sqshrn2 v6.8h, v16.4s, #3
  sqshrn2 v7.8h, v16.4s, #3
  sqshrn2 v8.8h, v16.4s, #3
  sqshrn2 v9.8h, v16.4s, #3
  sqshrn2 v10.8h, v16.4s, #3
  sqshrn2 v11.8h, v16.4s, #3
  sqshrn2 v12.8h, v16.4s, #3
  sqshrn2 v13.8h, v16.4s, #3
  sqshrn2 v14.8h, v16.4s, #3
  sqshrn2 v15.8h, v16.4s, #3
  movi v16.16b, 17

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2502

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)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440039300030251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011811600400361600001004004040040400404004040040
160204400393002430251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040
16020440039299030251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040
16020440039300051251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040
16020440039299030251601081001600081001600205001280132040020400394009019977619990160120200160032200320064400394003911160201100991001001600001002301111011801600400361600001004004040040400404004040040
160204400392990695251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040
16020440039300030251601081001600081001600205001280132140021400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040
16020440039299030251601081001600081001600205001280132140020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040
16020440039300030251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040
16020440039300330251601081001600081001600205001280132040020400394003919977619990160120200160032200320064400394003911160201100991001001600001000001111011801600400361600001004004040040400404004040040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)0318191e3f51inst 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)5f6061696d6edispatch 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)9fa1a7a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244005130000364625160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223115162116440036206160000104004040040400404004040040
1600244003929900516725160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223117162114540036206160000104004040040400404004040040
1600244003929900071125160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223116162113540036206160000104004040040400404004040040
160024400393000004625160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000002100223117162115540036206160000104004040040400404004040040
160024400393000004625160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223119162115540036206160000104004040040400404004040040
160024400392990004625160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223117162115340036206160000104004040040400404004040040
1600244003930000052251600101016000010160000501280000010400204003940039199963200191600102016000020320000400394003911160021109101016000010000001002462271642268400364012160000104004040040400404004040040
160024400393000005225160010101600001016000050128000001040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223118162117740036206160000104004040040400404004040040
160024400393000004625160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223115162116440036206160000104004040040400404004040040
160024400393000004625160010101600001016000050128000011040020400394003919996320019160010201600002032000040039400391116002110910101600001000000100223113162117440036206160000104004040040400404004040040