SHA256RNDS2 (XMM, XMM) - Port Usage

With blocking instructions for port '5':

Code:

   0:	66 0f 3a 21 dc 02    	insertps xmm3,xmm4,0x2
   6:	66 0f 3a 21 ec 02    	insertps xmm5,xmm4,0x2
   c:	66 0f 3a 21 f4 02    	insertps xmm6,xmm4,0x2
  12:	66 0f 3a 21 fc 02    	insertps xmm7,xmm4,0x2
  18:	66 44 0f 3a 21 c4 02 	insertps xmm8,xmm4,0x2
  1f:	66 44 0f 3a 21 cc 02 	insertps xmm9,xmm4,0x2
  26:	66 44 0f 3a 21 d4 02 	insertps xmm10,xmm4,0x2
  2d:	66 44 0f 3a 21 dc 02 	insertps xmm11,xmm4,0x2
  34:	66 44 0f 3a 21 e4 02 	insertps xmm12,xmm4,0x2
  3b:	66 0f 3a 21 dc 02    	insertps xmm3,xmm4,0x2
  41:	66 0f 3a 21 ec 02    	insertps xmm5,xmm4,0x2
  47:	66 0f 3a 21 f4 02    	insertps xmm6,xmm4,0x2
  4d:	66 0f 3a 21 fc 02    	insertps xmm7,xmm4,0x2
  53:	66 44 0f 3a 21 c4 02 	insertps xmm8,xmm4,0x2
  5a:	66 44 0f 3a 21 cc 02 	insertps xmm9,xmm4,0x2
  61:	66 44 0f 3a 21 d4 02 	insertps xmm10,xmm4,0x2
  68:	0f 38 cb ca          	sha256rnds2 xmm1,xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM3, [R14];
MOVUPD XMM4, [R14];
MOVUPD XMM5, [R14];
MOVUPD XMM6, [R14];
MOVUPD XMM7, [R14];
MOVUPD XMM8, [R14];
MOVUPD XMM9, [R14];
MOVUPD XMM10, [R14];
MOVUPD XMM11, [R14];
MOVUPD XMM12, [R14];
PXOR XMM1, XMM1;
PXOR XMM2, XMM2;
PXOR XMM0, XMM0

Show nanoBench command
Results:
- Instructions retired: 17.0
- Core cycles: 17.19
- Reference cycles: 13.11
- UOPS_PORT_5: 16.98

⇨ One μop that can only use port '5'

With blocking instructions for ports {'0', '1'}:

Code:

   0:	66 0f 58 dc          	addpd  xmm3,xmm4
   4:	66 0f 58 ec          	addpd  xmm5,xmm4
   8:	66 0f 58 f4          	addpd  xmm6,xmm4
   c:	66 0f 58 fc          	addpd  xmm7,xmm4
  10:	66 44 0f 58 c4       	addpd  xmm8,xmm4
  15:	66 44 0f 58 cc       	addpd  xmm9,xmm4
  1a:	66 44 0f 58 d4       	addpd  xmm10,xmm4
  1f:	66 44 0f 58 dc       	addpd  xmm11,xmm4
  24:	66 44 0f 58 e4       	addpd  xmm12,xmm4
  29:	66 0f 58 dc          	addpd  xmm3,xmm4
  2d:	66 0f 58 ec          	addpd  xmm5,xmm4
  31:	66 0f 58 f4          	addpd  xmm6,xmm4
  35:	66 0f 58 fc          	addpd  xmm7,xmm4
  39:	66 44 0f 58 c4       	addpd  xmm8,xmm4
  3e:	66 44 0f 58 cc       	addpd  xmm9,xmm4
  43:	66 44 0f 58 d4       	addpd  xmm10,xmm4
  48:	66 44 0f 58 dc       	addpd  xmm11,xmm4
  4d:	66 44 0f 58 e4       	addpd  xmm12,xmm4
  52:	66 0f 58 dc          	addpd  xmm3,xmm4
  56:	66 0f 58 ec          	addpd  xmm5,xmm4
  5a:	66 0f 58 f4          	addpd  xmm6,xmm4
  5e:	66 0f 58 fc          	addpd  xmm7,xmm4
  62:	66 44 0f 58 c4       	addpd  xmm8,xmm4
  67:	66 44 0f 58 cc       	addpd  xmm9,xmm4
  6c:	66 44 0f 58 d4       	addpd  xmm10,xmm4
  71:	66 44 0f 58 dc       	addpd  xmm11,xmm4
  76:	66 44 0f 58 e4       	addpd  xmm12,xmm4
  7b:	66 0f 58 dc          	addpd  xmm3,xmm4
  7f:	66 0f 58 ec          	addpd  xmm5,xmm4
  83:	66 0f 58 f4          	addpd  xmm6,xmm4
  87:	66 0f 58 fc          	addpd  xmm7,xmm4
  8b:	66 44 0f 58 c4       	addpd  xmm8,xmm4
  90:	0f 38 cb ca          	sha256rnds2 xmm1,xmm2,xmm0

Init:

VZEROALL;
MOV RAX, 0x4000000040000000;
MOV [R14+0], RAX;
MOV [R14+8], RAX;
MOVUPD XMM3, [R14];
MOVUPD XMM4, [R14];
MOVUPD XMM5, [R14];
MOVUPD XMM6, [R14];
MOVUPD XMM7, [R14];
MOVUPD XMM8, [R14];
MOVUPD XMM9, [R14];
MOVUPD XMM10, [R14];
MOVUPD XMM11, [R14];
MOVUPD XMM12, [R14];
PXOR XMM1, XMM1;
PXOR XMM2, XMM2;
PXOR XMM0, XMM0

Show nanoBench command
Results:
- Instructions retired: 33.0
- Core cycles: 16.39
- Reference cycles: 10.88
- UOPS_PORT_1: 16.0
- UOPS_PORT_0: 16.1

With blocking instructions for ports {'0', '1', '5'}:

Code:

   0:	66 0f 55 dc          	andnpd xmm3,xmm4
   4:	66 0f 55 ec          	andnpd xmm5,xmm4
   8:	66 0f 55 f4          	andnpd xmm6,xmm4
   c:	66 0f 55 fc          	andnpd xmm7,xmm4
  10:	66 44 0f 55 c4       	andnpd xmm8,xmm4
  15:	66 44 0f 55 cc       	andnpd xmm9,xmm4
  1a:	66 44 0f 55 d4       	andnpd xmm10,xmm4
  1f:	66 44 0f 55 dc       	andnpd xmm11,xmm4
  24:	66 44 0f 55 e4       	andnpd xmm12,xmm4
  29:	66 0f 55 dc          	andnpd xmm3,xmm4
  2d:	66 0f 55 ec          	andnpd xmm5,xmm4
  31:	66 0f 55 f4          	andnpd xmm6,xmm4
  35:	66 0f 55 fc          	andnpd xmm7,xmm4
  39:	66 44 0f 55 c4       	andnpd xmm8,xmm4
  3e:	66 44 0f 55 cc       	andnpd xmm9,xmm4
  43:	66 44 0f 55 d4       	andnpd xmm10,xmm4
  48:	66 44 0f 55 dc       	andnpd xmm11,xmm4
  4d:	66 44 0f 55 e4       	andnpd xmm12,xmm4
  52:	66 0f 55 dc          	andnpd xmm3,xmm4
  56:	66 0f 55 ec          	andnpd xmm5,xmm4
  5a:	66 0f 55 f4          	andnpd xmm6,xmm4
  5e:	66 0f 55 fc          	andnpd xmm7,xmm4
  62:	66 44 0f 55 c4       	andnpd xmm8,xmm4
  67:	66 44 0f 55 cc       	andnpd xmm9,xmm4
  6c:	66 44 0f 55 d4       	andnpd xmm10,xmm4
  71:	66 44 0f 55 dc       	andnpd xmm11,xmm4
  76:	66 44 0f 55 e4       	andnpd xmm12,xmm4
  7b:	66 0f 55 dc          	andnpd xmm3,xmm4
  7f:	66 0f 55 ec          	andnpd xmm5,xmm4
  83:	66 0f 55 f4          	andnpd xmm6,xmm4
  87:	66 0f 55 fc          	andnpd xmm7,xmm4
  8b:	66 44 0f 55 c4       	andnpd xmm8,xmm4
  90:	66 44 0f 55 cc       	andnpd xmm9,xmm4
  95:	66 44 0f 55 d4       	andnpd xmm10,xmm4
  9a:	66 44 0f 55 dc       	andnpd xmm11,xmm4
  9f:	66 44 0f 55 e4       	andnpd xmm12,xmm4
  a4:	66 0f 55 dc          	andnpd xmm3,xmm4
  a8:	66 0f 55 ec          	andnpd xmm5,xmm4
  ac:	66 0f 55 f4          	andnpd xmm6,xmm4
  b0:	66 0f 55 fc          	andnpd xmm7,xmm4
  b4:	66 44 0f 55 c4       	andnpd xmm8,xmm4
  b9:	66 44 0f 55 cc       	andnpd xmm9,xmm4
  be:	66 44 0f 55 d4       	andnpd xmm10,xmm4
  c3:	66 44 0f 55 dc       	andnpd xmm11,xmm4
  c8:	66 44 0f 55 e4       	andnpd xmm12,xmm4
  cd:	66 0f 55 dc          	andnpd xmm3,xmm4
  d1:	66 0f 55 ec          	andnpd xmm5,xmm4
  d5:	66 0f 55 f4          	andnpd xmm6,xmm4
  d9:	0f 38 cb ca          	sha256rnds2 xmm1,xmm2,xmm0

Init:

VZEROALL;
PXOR XMM3, XMM3;
PXOR XMM4, XMM4;
PXOR XMM5, XMM5;
PXOR XMM6, XMM6;
PXOR XMM7, XMM7;
PXOR XMM8, XMM8;
PXOR XMM9, XMM9;
PXOR XMM10, XMM10;
PXOR XMM11, XMM11;
PXOR XMM12, XMM12;
PXOR XMM1, XMM1;
PXOR XMM2, XMM2;
PXOR XMM0, XMM0

Show nanoBench command
Results:
- Instructions retired: 49.0
- Core cycles: 17.45
- Reference cycles: 11.5
- UOPS_PORT_1: 16.7
- UOPS_PORT_0: 16.5
- UOPS_PORT_5: 16.9

⇨ One μop that can only use ports {'0', '1', '5'}