Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRN (D)

Test 1: uops

Code:

  sqrshrn s0, d0, #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)0318191e1f3a3f4e51inst 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)a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230000061254725100010001000398160030183037303724143289510001000100030373037111001100000000073116112629100030383038303830383038
10043037230000061254725100010001000398160030183037303724143289510001000100030373037111001100000900073116112629100030383038303830383038
10043037240000082254725100010001000398160130183037303724143289510001000100030373037111001100000000073116112629100030383038303830383085
10043037240000061254725100010001000398160130543037303724143289510001000100030373037111001100000000073116112629100030383038303830383038
10043037240000061254725100010001000398160130183037303724143289510001000100030373037111001100000000073116112629100030383038303830383038
10043037230000061254725100010001000398160130183037303724143289510001000100030373037111001100000100073116112629100030383038303830383038
100430372400000117211825100010001000398160030183037303724143289510001000100030373037111001100000003073116112629100030383038303830383038
100430372400000612547251000100010003981600301830373037241432895100010001000303730371110011000000087073116112629100030383038303830383038
1004303724000009432547251000100010003981600301830373037241432895100010001000308430371110011000001099073116112629100030383038303830383038
10043037230090061254725100010001000398160030183037303724143289510001000100030373037111001100000000073116112629100030383086303830383038

Test 2: Latency 1->2

Code:

  sqrshrn s0, d0, #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)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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723301000017606129547251010010010000100100005004277160130018030037300372826823287571010020010167200101613003730037211020110099100100100001000000000071011641296330100001003003830038300383003830038
1020430037232000000001052954725101001001000810010000500427716013001803003730037282643287451027520410000200101663003730037111020110099100100100001000000000071011611296690100001003003830038300383003830085
1020430037233000000006129547251010010010000100100005004279864130018030037302272826419287791010020010335200100003008530037111020110099100100100001000000000071011611296330100001003003830085300383003830038
1020430037233000000007892954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000020000071011611296332100001003051530519305143051830369
10204304982350019111320880065402945721510236155100881481120080542906801304140303723051128300582894611806238116592361165830547303601111020110099100100100001000000143052009852105313002929100001003056030515305553042130611
102043056723610011107959000716529448228102441561008815610900783429068013001803003730037282643287451010020010167200100003003730131111020110099100100100001000000002810071011611296330100001003003830038300383007530038
102043003723200000000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000000000075834311296332100001003003830038300383003830038
102043003723200000000612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037211020110099100100100001000020002790071011611296330100001003003830134300383003830038
10204300372330000000010629547251010010010000100100005004279864130054030037300372826417287451010020210332200100003003730037311020110099100100100001000000000073411612296330100001003003830038300383013430038
102043003723200000000822953861101401281000010010150500427716013001803008530180282643287451010020010000200100003008830037211020110099100100100001000000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037241000000027392954725100101210000101000050427716003012630037300372828632876710010201000020100003003730037111002110910101000010000000006403162229629010000103003830038300383003830038
10024300372330000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243008424900100007042954725100191110000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103008630038300383013230038
10024300372330000000612952925100101210000101000050427716003005430037300372828632876710161201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372330000013288612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010200000006402162229629010000103003830038300383003830038
1002430037233000200196612954725100101010000101000050427716003001830037300372828632876710010201000020101633003730037111002110910101000010000000006402162329665010000103003830038300383003830038
10024301312320000000612954725100101010000101015055427716003001830037300852829032876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383008530038
10024300372330000000612954725100101010000101000050427716003001830037300372828632876710313201000020100003003730037111002110910101000010000000006402162229629110000103003830038300383003830038
10024300372330000000612954725100101010000101000061427716003009030037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103008630038300853003830134
10024300372320000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229701210000103003830132300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrn s0, d8, #3
  sqrshrn s1, d8, #3
  sqrshrn s2, d8, #3
  sqrshrn s3, d8, #3
  sqrshrn s4, d8, #3
  sqrshrn s5, d8, #3
  sqrshrn s6, d8, #3
  sqrshrn s7, d8, #3
  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)030408090b18191e1f3a3f51inst 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)9fa1a6a7a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391550001000025225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151227168820036800001002004020040200402004020040
8020420106161010000180228325801081008000810080020500640132120020200392003999776999080120200800322008003220039200393180201100991001008000010000000011151228166620036800001002004020040200402004020040
80204200391560000000023125801081008000810080020500640132120020200392003999776999080120200800322008003220039200392180201100991001008000010040000011151228168820036800001002004020040200402004020040
8020420039155000000017623125801081008000810080128500640132120020200392003999866999080120200800322008003220039200391180201100991001008000010000000011151438168820036800001002004020040200402004020040
80204200391550000000023125801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151228168820036800001002004020040200402004020040
80204200391550000000023125801081008000810080020500640132120020200392009299776999080120200800322008003220039200391180201100991001008000010000000011151228168320036800001002004020040200402004020040
80204200391550000000023125801081008000810080020500640132120020200392003999776999080120200800322008003220111200391180201100991001008000010000000011151228169820036800001002004020040200402004020040
80204200391610000200023125801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151228168320036800001002023320040200402004020040
802042011015500000000231258010810080008100800205006401321200202003920039997761004580120200800322008003220039200391180201100991001008000010000000011151228168820036800001002004020040200402004020040
80204200391550000000027525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151224168820036800001002004020096200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090a0b18191e1f3a3f51inst 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)9fa0a6acc2cfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915500000000126258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050207164762003680000102004020040200402004020040
80024200391550000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010003050204160962003680000102004020040200402004020040
80024200391570000000083258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050207162442003680000102004020040200402004020040
80024200391551000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050204162842003680000102004020040200402004020040
80024200391550000000040258001010800001080000506457120200202003920039999631001980010208000020800002003920039118002110910108000010000050204350462003680000102004020040200402004020040
80024200391550000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039218002110910108000010000050204162872003680000102004020040200402004020040
80024200391550000000040258001012800001080000506400000200792003920039999671001980010208000020800002003920039118002110910108000010000050208160542003680000102004020040200402004020040
80024200391550000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050207350972003680000102004020040200402004020040
80024200391550000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050207160542003680000102004020040200402004020040
80024200391560000000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050206160752003680000102004020040200402004020040