Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRUN (S)

Test 1: uops

Code:

  sqrshrun 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)03071e3f4e51inst 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
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000073316222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110003073216222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723096125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230021425472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723006125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037230061254725100010001000398160130543037303724143289510001000100030373037111001100001873216222629100030383038303830383038
1004303722006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrun 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)030818191e3f4e51inst 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)9fa6a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000120929547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037225000090329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037225000098029547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037225000014529547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000074911611296330100001003003830038300383003830038
1020430037233000099529547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100002913071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003722500006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
10204300372250000102629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037225000091329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037225000097729547251010011010000100100005004277160030018300373003728271728741101002001000820010008300373003711102011009910010010000100000171011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a1e1f3a3f4e51inst 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)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372251010026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000644101610112962910000103003830038300383003830038
10024300372251010026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000644101611102962910000103003830038300383003830038
1002430037225101002682954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000064411165102962910000103003830038300383003830038
10024300372251010026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101000644101610102962910000103003830038300383003830038
10024300372251010026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101010644111610102962910000103003830038300383003830038
100243003722510100268295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001015100644101610102962910000103003830038300383003830038
10024300372251010026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101000644101610102962910000103003830038300383003830038
1002430037225101002682954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000064461610102962910000103003830038300383003830038
10024300372321010029629511251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000644101611112962910000103003830038300383003830038
10024300372251010026829547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110022109101010000100000644101610102962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqrshrun h0, s8, #3
  sqrshrun h1, s8, #3
  sqrshrun h2, s8, #3
  sqrshrun h3, s8, #3
  sqrshrun h4, s8, #3
  sqrshrun h5, s8, #3
  sqrshrun h6, s8, #3
  sqrshrun 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): 0.2505

retire (01)cycle (02)030f1e3a3f51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391540005125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000030011151180160020036800001002004020040200402004020040
80204200391500003025801081008010810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
8020420039150000101625801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500007225801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000010011151180160020036800001002004020040200402004020040
80204200391500003097801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
802042003915000015625801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040
80204200391500005125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151180160020036800001002004020040200402004020040

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)9fa0a1a6a8accfd5d6d9dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000503781600462003680000102004020040200402004020040
80024200391490012425800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502041600462003680000102004020040200402004020040
80024200391500019325800101080000108010450640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502051600462003680000102004020040200402004020040
80024200391500014525800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502061600642003680000102004020040200402004020040
800242003915000161825800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502061600642003680000102004020040200402004020040
80024200391500019325800101080000108000050640000120020200392003999963100198001020800002080000201002003911800211091010800001000000502061600472003680000102004020040200402004020040
80024200391500010325800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502061600752003680000102004020040200402004020040
80024200391500019125800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502041600682003680000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502061600672003680000102004020040200402004020040
80024200391500012425800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502071600462003680000102004020040200402004020040