Apple M1 Microarchitecture Research by Dougall Johnson

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

SRSHR (vector, D)

Test 1: uops

Code:

  srshr d0, 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)03080b1e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)6061696d6edispatch 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)a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220002512547251000100010003981600730183037303724143289510001000100030373037111001100003737116112629100030383038303830383038
1004303723000612547251000100010003981601730183037303724143289510001000100030373037111001100000737116112629100030383038303830383038
1004303722000612547251000100010003981601730183037303724143289510001000100030373037111001100000737116112629100030383038303830383038
10043037231012612547251000100010003981601730183037303724143289510001000100030373037111001100000737116112629100030383038303830383038
10043037230015612547251000100010003981601730183037303724143289510001000100030373037111001100010737116112629100030383038303830383038
1004303722000612547251000100010003981601730183037303724143289510001000100030373037111001100000737116112629100030383038303830383038
1004303722000612547251000100010003981600730183037303724143289510001000100030373037111001100000737116112629100030383038303830383038
1004303722000612547251000100010003981601730183037303724143289510001000100030373037111001100000737116112629100030383038303830383038
1004303723000612547251000100010003981601730183037303724143289510001000100030373037111001100000737116112629100030383038303830383038
1004303723000612547251000100010003981601730183037303724143289510001000100030373037111001100040737116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  srshr d0, 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)030408090b18191e1f3f4e51inst 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)9fa0a1a8a9acc2cficache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225100000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100001030710021622296330100001003003830038300383003830038
10204300372250000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000037000710021642296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160030018300373003728264828745101002001000020010000300373003711102011009910010010000100001000710021622296330100001003003830038300383003830038
1020430074225000000001032954725101001001000010010000500427716003001830037300372826418287451010020010000200100003003730037111020110099100100100001000044060710021622296330100001003003830038300383003830038
1020430037225000000429023129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710021622296330100001003003830038300383003830038
10204300372250000004290612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300375110201100991001001000010000120120710021632296330100001003003830038300383003830038
10204300372250000002706129547251010010010000100100005004277160030018300373003728264328745101002001000020010000301803003711102011009910010010000100002000710021622296330100001003003830038300383003830038
1020430037225000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100001000710031622296330100001003003830038302303003830038
1020430037225000000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100001000710021622296330100001003003830038300383021930038
1020430037225000000006129547251010012010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080918191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010206402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722400000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010406402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010406402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010096402162229629010000103003830038300383003830038
10024300372250000361032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830085300383003830038
100243003722500006612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010096402162229629010000103003830038300383003830179
100243003722400000612954725100101010000101000055427716003001830037300372828632876710010201000020100003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  srshr d0, d8, #3
  srshr d1, d8, #3
  srshr d2, d8, #3
  srshr d3, d8, #3
  srshr d4, d8, #3
  srshr d5, d8, #3
  srshr d6, d8, #3
  srshr d7, 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)030b18191e1f3f51inst 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)9fa0a6a8acc5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601510000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181620036800001002004020040200402004020040
802042003915000027030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000311151181620036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100004011151181620036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181620036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181620036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100002011151181620036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181620036800001002004020040201422004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181620036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181620036800001002004020040200402004020040
80204200391500000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151181620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020316112003680000102004020040200402024720040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020216112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208010420800002003920039118002110910108000010105020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010305020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020116112003680000102004020040200402004020040