Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHRN (8H)

Test 1: uops

Code:

  sqshrn v0.8b, v0.8h, #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)03181e3f4e51inst 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
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000373216112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037231061254725100010001000398160030183037303724143289510001000100030373037111001100017073116112629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722066125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqshrn v0.8b, v0.8h, #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)6061696d6edispatch 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954725101001001000010010369500427716010300183003730037282640328745101002001000020010000300373003711102011009901001001000010020071002162229633100001003003830038300383003830038
102043003722503792954725101001001000010010000500427716010300183003730037282640328745101002001000020010000300373003711102011009951001001000010000071002162229633100001003003830038300383003830038
102043003722504272954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038
102043003722504402954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038
102043003722508702954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038
102043003722507962954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038
102043003722509532954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038
102043003722509342954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038
102043003722503612954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038
102043003722509192954725101001001000010010000500427716000300183003730037282640328745101002001000020010000300373003711102011009901001001000010000071002162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)696d6edispatch 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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000001079295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000001000295472510010101000010100005042771603001830037300372828632876710010201000020101723003730037111002110910101000010100000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000987295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000009006402162229629010000103003830038300383003830038
100243003722500000993295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000001075295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000896295472510010101000010100005042771603001830037300372830132876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
1002430037225000001046295472510010101000010100005042771603001830037300372828632876710010201000020100003003730037111002110910101000010000200006402162229629010000103003830038300383003830038
1002430037225000001057295472510010101000012100005042771603001830037300372828632876710012201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqshrn v0.8b, v8.8h, #3
  sqshrn v1.8b, v8.8h, #3
  sqshrn v2.8b, v8.8h, #3
  sqshrn v3.8b, v8.8h, #3
  sqshrn v4.8b, v8.8h, #3
  sqshrn v5.8b, v8.8h, #3
  sqshrn v6.8b, v8.8h, #3
  sqshrn v7.8b, v8.8h, #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)0308090b191e1f3f51inst 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)696d6edispatch 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500000003025801081008000810080020500640132200202003920039997761002380120200800322008003220039200391180201100991001008000010000011151184163320036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184164320036800001002004020040200402004020040
8020420039150000000302580108100801081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184163420098800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184163420036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163420036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151184163420036800001002004020040200402004020040
8020420039150000000952580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010010011151184163420036800001002004020040200402004020040
8020420039150000000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183163420036800001002004020040200402004020040
8020420039150000000512580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151182164320036800001002004020040200402004020040
80204200391500000005972580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010009011151184164420036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)696d6edispatch 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)9fa6a8accfd0itlb miss (d4)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150008225800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502141171617172003680000102004020040200402004020040
80024200391501070525800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502101171614172003680000102004020040200402004020040
8002420039150104025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502000171613172003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001001050200091617142003680000102004020040200402004020040
800242003915000114925800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502000141617142003680000102004020040200402004020040
8002420039150006125800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010010502000171616172003680000102004020040200402004020040
8002420039150004025800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502000141617142003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200091617142003680000102004020040200402004020040
80024200391500058425800101080000108000050640000200202003920039999631001980010208000020800002003920039118002110910108000010000502000171617172003680000102004020040200402004020040
800242003915000402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050200017169172003680000102004020040200402004020040