Apple M1 Microarchitecture Research by Dougall Johnson

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

FRSQRTE (scalar, D)

Test 1: uops

Code:

  frsqrte d0, d0
  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
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372206119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
1004303722017019002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372236119002510001000100010445113018303730372738328951000100010003037303711100110001073116112919100030383038303830383038
100430372206119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372306119002510001000100010445113018303730372738328951000100010003037303711100110000073116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  frsqrte d0, d0
  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)03181e3f4e51inst 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)696b6d6edispatch 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
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007103162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003008530038300383003830038
1020430037225006119900251010010010000100100005001067451300180300373003728588328745101002001000020010000300373003711102011009910010010000100007102162229919100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090a0b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000061199002510010101000010100005010674510300183008430037286283287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674510300183003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
100243003722500000012066199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674511300543003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
10024300372240000000061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
100243003722400000000726199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000002006402162229919010000103003830038300383003830038
10024300372250000000061199002510010101000010100005010674511300183003730037286103287671001020100002010000300373003711100211091010100001000000006402162229919010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frsqrte d0, d8
  frsqrte d1, d8
  frsqrte d2, d8
  frsqrte d3, d8
  frsqrte d4, d8
  frsqrte d5, d8
  frsqrte d6, d8
  frsqrte d7, d8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)03081e1f3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020480041600000704258010010080000100800005006400000800200800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008023880040800408004080040
802048003960000039258010010080000100800005006400001800200800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080040
802048003959900039258010010080000100800005006400000800200800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080040
802048003960000039258010010080000100800005006400000800200800398003969971669993801002008000820080008800398003911802021009910010080000100230111511716080036800001008004080040800408004080040
802048003960000081258010010080000100800005006400000800200800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080040
8020480039599000188258010010080000100800005006400000800200800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080090
802048003959910039258010010080000100800005006400000800203800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080040
802048003959900039258010010080000100800005006400000800200800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080040
802048003960000039258010010080000100800005006400000800200800398003969971669993801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080040
802048003959900039258010010080000100800005006400000800200800398003969971670027801002008000820080008800398003911802011009910010080000100000111511716080036800001008004080040800408004080040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)0308191e3f51inst 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)5f60696b6d6edispatch 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)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a7a8a9acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002480039600002750258001010800001080000506400000080020080039800396998603700198001020800002080000800398003911800211091010800001000005105020000416076800341780000108004080040800408004080040
800248003960000050258001010800001080000506400000180020080039800396998603700198001020800002080000800398003911800211091010800001000001770502000041604380034080000108004080040800408004080040
800248003960100050258001010800001080000506400000180020080039800396998603700198001020800002080000800398003911800211091010800001000001500502000031604480034080000108004080040800408004080040
800248003960000050258001010800001080000506400000180020080039800396998603700198001020800002080000800398003911800211091010800001000001291502000041606680034080000108004080040800408004080040
800248003960000050258001010800001080000506400000080020080039800396998603700198001020800002080000800398003911800211091010800001000001110502000041603480034080000108004080040800408004080040
800248003960000050258001010800001080000506400000080020080039800396998603700198001020800002080000800398003911800211091010800001000001080502000061603480034080000108004080040800408004080040
800248003959900050258001010800001080000506400000180020080039800396998603700198001020800402080000800398003911800211091010800001000202130502000074904480034080000108004080040800408004080040
80024802365990006578258001010800001080000506400000080020080039800396998603700198001020800002080000800398003911800211091010800001000002400502000041604380034080000108004080040800408004080040
800248003960000050258001010800001080000506400000080020080039800396998603700198001020800002080000800398003911800211091010800001000001950502000041603480034080000108004080040800408004080040
800248003960000050258001010800001080000506400000180020080039800396998603700198001020800002080000800398003911800211091010800001000001170502000031604480034080000108004080040800408004080040