2008-04-23 H.J. Lu <hongjiu.lu@intel.com>
authorH.J. Lu <hjl.tools@gmail.com>
Wed, 23 Apr 2008 14:34:05 +0000 (14:34 +0000)
committerH.J. Lu <hjl.tools@gmail.com>
Wed, 23 Apr 2008 14:34:05 +0000 (14:34 +0000)
* gas/i386/sse2.s: Add tests for pmuludq, paddq and psubq.
* gas/i386/x86-64-simd.s: Likewise.

* gas/i386/sse2.d: Updated.
* gas/i386/x86-64-simd.d: Likewise.
* gas/i386/x86-64-simd-intel.d: Likewise.
* gas/i386/x86-64-simd-suffix.d: Likewise.

gas/testsuite/ChangeLog
gas/testsuite/gas/i386/sse2.d
gas/testsuite/gas/i386/sse2.s
gas/testsuite/gas/i386/x86-64-simd-intel.d
gas/testsuite/gas/i386/x86-64-simd-suffix.d
gas/testsuite/gas/i386/x86-64-simd.d
gas/testsuite/gas/i386/x86-64-simd.s

index a331751..871508e 100644 (file)
@@ -1,3 +1,13 @@
+2008-04-23  H.J. Lu  <hongjiu.lu@intel.com>
+
+       * gas/i386/sse2.s: Add tests for pmuludq, paddq and psubq.
+       * gas/i386/x86-64-simd.s: Likewise.
+
+       * gas/i386/sse2.d: Updated.
+       * gas/i386/x86-64-simd.d: Likewise.
+       * gas/i386/x86-64-simd-intel.d: Likewise.
+       * gas/i386/x86-64-simd-suffix.d: Likewise.
+
 2008-04-23  David S. Miller  <davem@davemloft.net>
 
        * gas/sparc/pc2210.d: New file.
index 55ebb13..0c87e86 100644 (file)
 Disassembly of section .text:
 
 0+ <foo>:
-[      ]+0:    0f c3 00[       ]+movnti %eax,\(%eax\)
-[      ]+3:    0f ae f8[       ]+sfence 
-[      ]+6:    0f ae e8[       ]+lfence 
-[      ]+9:    0f ae f0[       ]+mfence 
-[      ]+c:    66 0f 58 01[    ]+addpd[        ]+\(%ecx\),%xmm0
-[      ]+10:   66 0f 58 ca[    ]+addpd[        ]+%xmm2,%xmm1
-[      ]+14:   f2 0f 58 13[    ]+addsd[        ]+\(%ebx\),%xmm2
-[      ]+18:   f2 0f 58 dc[    ]+addsd[        ]+%xmm4,%xmm3
-[      ]+1c:   66 0f 55 65 00[         ]+andnpd 0x0\(%ebp\),%xmm4
-[      ]+21:   66 0f 55 ee[    ]+andnpd %xmm6,%xmm5
-[      ]+25:   66 0f 54 37[    ]+andpd[        ]+\(%edi\),%xmm6
-[      ]+29:   66 0f 54 f8[    ]+andpd[        ]+%xmm0,%xmm7
-[      ]+2d:   66 0f c2 c1 02[         ]+cmplepd %xmm1,%xmm0
-[      ]+32:   66 0f c2 0a 03[         ]+cmpunordpd \(%edx\),%xmm1
-[      ]+37:   f2 0f c2 d2 04[         ]+cmpneqsd %xmm2,%xmm2
-[      ]+3c:   f2 0f c2 1c 24 05[      ]+cmpnltsd \(%esp\),%xmm3
-[      ]+42:   66 0f c2 e5 06[         ]+cmpnlepd %xmm5,%xmm4
-[      ]+47:   66 0f c2 2e 07[         ]+cmpordpd \(%esi\),%xmm5
-[      ]+4c:   f2 0f c2 f7 00[         ]+cmpeqsd %xmm7,%xmm6
-[      ]+51:   f2 0f c2 38 01[         ]+cmpltsd \(%eax\),%xmm7
-[      ]+56:   66 0f c2 c1 00[         ]+cmpeqpd %xmm1,%xmm0
-[      ]+5b:   66 0f c2 0a 00[         ]+cmpeqpd \(%edx\),%xmm1
-[      ]+60:   f2 0f c2 d2 00[         ]+cmpeqsd %xmm2,%xmm2
-[      ]+65:   f2 0f c2 1c 24 00[      ]+cmpeqsd \(%esp\),%xmm3
-[      ]+6b:   66 0f c2 e5 01[         ]+cmpltpd %xmm5,%xmm4
-[      ]+70:   66 0f c2 2e 01[         ]+cmpltpd \(%esi\),%xmm5
-[      ]+75:   f2 0f c2 f7 01[         ]+cmpltsd %xmm7,%xmm6
-[      ]+7a:   f2 0f c2 38 01[         ]+cmpltsd \(%eax\),%xmm7
-[      ]+7f:   66 0f c2 01 02[         ]+cmplepd \(%ecx\),%xmm0
-[      ]+84:   66 0f c2 ca 02[         ]+cmplepd %xmm2,%xmm1
-[      ]+89:   f2 0f c2 13 02[         ]+cmplesd \(%ebx\),%xmm2
-[      ]+8e:   f2 0f c2 dc 02[         ]+cmplesd %xmm4,%xmm3
-[      ]+93:   66 0f c2 65 00 03[      ]+cmpunordpd 0x0\(%ebp\),%xmm4
-[      ]+99:   66 0f c2 ee 03[         ]+cmpunordpd %xmm6,%xmm5
-[      ]+9e:   f2 0f c2 37 03[         ]+cmpunordsd \(%edi\),%xmm6
-[      ]+a3:   f2 0f c2 f8 03[         ]+cmpunordsd %xmm0,%xmm7
-[      ]+a8:   66 0f c2 c1 04[         ]+cmpneqpd %xmm1,%xmm0
-[      ]+ad:   66 0f c2 0a 04[         ]+cmpneqpd \(%edx\),%xmm1
-[      ]+b2:   f2 0f c2 d2 04[         ]+cmpneqsd %xmm2,%xmm2
-[      ]+b7:   f2 0f c2 1c 24 04[      ]+cmpneqsd \(%esp\),%xmm3
-[      ]+bd:   66 0f c2 e5 05[         ]+cmpnltpd %xmm5,%xmm4
-[      ]+c2:   66 0f c2 2e 05[         ]+cmpnltpd \(%esi\),%xmm5
-[      ]+c7:   f2 0f c2 f7 05[         ]+cmpnltsd %xmm7,%xmm6
-[      ]+cc:   f2 0f c2 38 05[         ]+cmpnltsd \(%eax\),%xmm7
-[      ]+d1:   66 0f c2 01 06[         ]+cmpnlepd \(%ecx\),%xmm0
-[      ]+d6:   66 0f c2 ca 06[         ]+cmpnlepd %xmm2,%xmm1
-[      ]+db:   f2 0f c2 13 06[         ]+cmpnlesd \(%ebx\),%xmm2
-[      ]+e0:   f2 0f c2 dc 06[         ]+cmpnlesd %xmm4,%xmm3
-[      ]+e5:   66 0f c2 65 00 07[      ]+cmpordpd 0x0\(%ebp\),%xmm4
-[      ]+eb:   66 0f c2 ee 07[         ]+cmpordpd %xmm6,%xmm5
-[      ]+f0:   f2 0f c2 37 07[         ]+cmpordsd \(%edi\),%xmm6
-[      ]+f5:   f2 0f c2 f8 07[         ]+cmpordsd %xmm0,%xmm7
-[      ]+fa:   66 0f 2f c1[    ]+comisd %xmm1,%xmm0
-[      ]+fe:   66 0f 2f 0a[    ]+comisd \(%edx\),%xmm1
- 102:  66 0f 2a d3[    ]+cvtpi2pd %mm3,%xmm2
- 106:  66 0f 2a 1c 24[         ]+cvtpi2pd \(%esp\),%xmm3
- 10b:  f2 0f 2a e5[    ]+cvtsi2sd %ebp,%xmm4
- 10f:  f2 0f 2a 2e[    ]+cvtsi2sdl \(%esi\),%xmm5
- 113:  66 0f 2d f7[    ]+cvtpd2pi %xmm7,%mm6
- 117:  66 0f 2d 38[    ]+cvtpd2pi \(%eax\),%mm7
- 11b:  f2 0f 2d 01[    ]+cvtsd2si \(%ecx\),%eax
- 11f:  f2 0f 2d ca[    ]+cvtsd2si %xmm2,%ecx
- 123:  66 0f 2c 13[    ]+cvttpd2pi \(%ebx\),%mm2
- 127:  66 0f 2c dc[    ]+cvttpd2pi %xmm4,%mm3
- 12b:  f2 0f 2c 65 00[         ]+cvttsd2si 0x0\(%ebp\),%esp
- 130:  f2 0f 2c ee[    ]+cvttsd2si %xmm6,%ebp
- 134:  66 0f 5e c1[    ]+divpd[        ]+%xmm1,%xmm0
- 138:  66 0f 5e 0a[    ]+divpd[        ]+\(%edx\),%xmm1
- 13c:  f2 0f 5e d3[    ]+divsd[        ]+%xmm3,%xmm2
- 140:  f2 0f 5e 1c 24[         ]+divsd[        ]+\(%esp\),%xmm3
- 145:  0f ae 55 00[    ]+ldmxcsr 0x0\(%ebp\)
- 149:  0f ae 1e[       ]+stmxcsr \(%esi\)
- 14c:  0f ae f8[       ]+sfence 
- 14f:  66 0f 5f c1[    ]+maxpd[        ]+%xmm1,%xmm0
- 153:  66 0f 5f 0a[    ]+maxpd[        ]+\(%edx\),%xmm1
- 157:  f2 0f 5f d3[    ]+maxsd[        ]+%xmm3,%xmm2
- 15b:  f2 0f 5f 1c 24[         ]+maxsd[        ]+\(%esp\),%xmm3
- 160:  66 0f 5d e5[    ]+minpd[        ]+%xmm5,%xmm4
- 164:  66 0f 5d 2e[    ]+minpd[        ]+\(%esi\),%xmm5
- 168:  f2 0f 5d f7[    ]+minsd[        ]+%xmm7,%xmm6
- 16c:  f2 0f 5d 38[    ]+minsd[        ]+\(%eax\),%xmm7
- 170:  66 0f 28 c1[    ]+movapd %xmm1,%xmm0
- 174:  66 0f 29 11[    ]+movapd %xmm2,\(%ecx\)
- 178:  66 0f 28 12[    ]+movapd \(%edx\),%xmm2
- 17c:  66 0f 17 2c 24[         ]+movhpd %xmm5,\(%esp\)
- 181:  66 0f 16 2e[    ]+movhpd \(%esi\),%xmm5
- 185:  66 0f 13 07[    ]+movlpd %xmm0,\(%edi\)
- 189:  66 0f 12 00[    ]+movlpd \(%eax\),%xmm0
- 18d:  66 0f 50 ca[    ]+movmskpd %xmm2,%ecx
- 191:  66 0f 10 d3[    ]+movupd %xmm3,%xmm2
- 195:  66 0f 11 22[    ]+movupd %xmm4,\(%edx\)
- 199:  66 0f 10 65 00[         ]+movupd 0x0\(%ebp\),%xmm4
- 19e:  f2 0f 10 ee[    ]+movsd[        ]+%xmm6,%xmm5
- 1a2:  f2 0f 11 3e[    ]+movsd[        ]+%xmm7,\(%esi\)
- 1a6:  f2 0f 10 38[    ]+movsd[        ]+\(%eax\),%xmm7
- 1aa:  66 0f 59 c1[    ]+mulpd[        ]+%xmm1,%xmm0
- 1ae:  66 0f 59 0a[    ]+mulpd[        ]+\(%edx\),%xmm1
- 1b2:  f2 0f 59 d2[    ]+mulsd[        ]+%xmm2,%xmm2
- 1b6:  f2 0f 59 1c 24[         ]+mulsd[        ]+\(%esp\),%xmm3
- 1bb:  66 0f 56 e5[    ]+orpd[         ]+%xmm5,%xmm4
- 1bf:  66 0f 56 2e[    ]+orpd[         ]+\(%esi\),%xmm5
- 1c3:  66 0f c6 37 02[         ]+shufpd \$0x2,\(%edi\),%xmm6
- 1c8:  66 0f c6 f8 03[         ]+shufpd \$0x3,%xmm0,%xmm7
- 1cd:  66 0f 51 c1[    ]+sqrtpd %xmm1,%xmm0
- 1d1:  66 0f 51 0a[    ]+sqrtpd \(%edx\),%xmm1
- 1d5:  f2 0f 51 d2[    ]+sqrtsd %xmm2,%xmm2
- 1d9:  f2 0f 51 1c 24[         ]+sqrtsd \(%esp\),%xmm3
- 1de:  66 0f 5c e5[    ]+subpd[        ]+%xmm5,%xmm4
- 1e2:  66 0f 5c 2e[    ]+subpd[        ]+\(%esi\),%xmm5
- 1e6:  f2 0f 5c f7[    ]+subsd[        ]+%xmm7,%xmm6
- 1ea:  f2 0f 5c 38[    ]+subsd[        ]+\(%eax\),%xmm7
- 1ee:  66 0f 2e 01[    ]+ucomisd \(%ecx\),%xmm0
- 1f2:  66 0f 2e ca[    ]+ucomisd %xmm2,%xmm1
- 1f6:  66 0f 15 13[    ]+unpckhpd \(%ebx\),%xmm2
- 1fa:  66 0f 15 dc[    ]+unpckhpd %xmm4,%xmm3
- 1fe:  66 0f 14 65 00[         ]+unpcklpd 0x0\(%ebp\),%xmm4
- 203:  66 0f 14 ee[    ]+unpcklpd %xmm6,%xmm5
- 207:  66 0f 57 37[    ]+xorpd[        ]+\(%edi\),%xmm6
- 20b:  66 0f 57 f8[    ]+xorpd[        ]+%xmm0,%xmm7
- 20f:  66 0f 2b 33[    ]+movntpd %xmm6,\(%ebx\)
- 213:  66 0f 57 c8[    ]+xorpd[        ]+%xmm0,%xmm1
- 217:  f3 0f e6 c8[    ]+cvtdq2pd %xmm0,%xmm1
- 21b:  f2 0f e6 c8[    ]+cvtpd2dq %xmm0,%xmm1
- 21f:  0f 5b c8[       ]+cvtdq2ps %xmm0,%xmm1
- 222:  66 0f 5a c8[    ]+cvtpd2ps %xmm0,%xmm1
- 226:  0f 5a c8[       ]+cvtps2pd %xmm0,%xmm1
- 229:  66 0f 5b c8[    ]+cvtps2dq %xmm0,%xmm1
- 22d:  f2 0f 5a c8[    ]+cvtsd2ss %xmm0,%xmm1
- 231:  f3 0f 5a c8[    ]+cvtss2sd %xmm0,%xmm1
- 235:  66 0f e6 c8[    ]+cvttpd2dq %xmm0,%xmm1
- 239:  f3 0f 5b c8[    ]+cvttps2dq %xmm0,%xmm1
- 23d:  66 0f f7 c8[    ]+maskmovdqu %xmm0,%xmm1
- 241:  66 0f 6f c8[    ]+movdqa %xmm0,%xmm1
- 245:  66 0f 7f 06[    ]+movdqa %xmm0,\(%esi\)
- 249:  f3 0f 6f c8[    ]+movdqu %xmm0,%xmm1
- 24d:  f3 0f 7f 06[    ]+movdqu %xmm0,\(%esi\)
- 251:  f2 0f d6 c8[    ]+movdq2q %xmm0,%mm1
- 255:  f3 0f d6 c8[    ]+movq2dq %mm0,%xmm1
- 259:  66 0f f4 c8[    ]+pmuludq %xmm0,%xmm1
- 25d:  66 0f f4 c8[    ]+pmuludq %xmm0,%xmm1
- 261:  66 0f 70 c8 01[         ]+pshufd \$0x1,%xmm0,%xmm1
- 266:  f3 0f 70 c8 01[         ]+pshufhw \$0x1,%xmm0,%xmm1
- 26b:  f2 0f 70 c8 01[         ]+pshuflw \$0x1,%xmm0,%xmm1
- 270:  66 0f 73 f8 01[         ]+pslldq \$0x1,%xmm0
- 275:  66 0f 73 d8 01[         ]+psrldq \$0x1,%xmm0
- 27a:  66 0f 6d c8[    ]+punpckhqdq %xmm0,%xmm1
- 27e:  66 90[  ]+xchg[         ]+%ax,%ax
+[      ]*[a-f0-9]+:    0f c3 00                movnti %eax,\(%eax\)
+[      ]*[a-f0-9]+:    0f ae f8                sfence 
+[      ]*[a-f0-9]+:    0f ae e8                lfence 
+[      ]*[a-f0-9]+:    0f ae f0                mfence 
+[      ]*[a-f0-9]+:    66 0f 58 01             addpd  \(%ecx\),%xmm0
+[      ]*[a-f0-9]+:    66 0f 58 ca             addpd  %xmm2,%xmm1
+[      ]*[a-f0-9]+:    f2 0f 58 13             addsd  \(%ebx\),%xmm2
+[      ]*[a-f0-9]+:    f2 0f 58 dc             addsd  %xmm4,%xmm3
+[      ]*[a-f0-9]+:    66 0f 55 65 00          andnpd 0x0\(%ebp\),%xmm4
+[      ]*[a-f0-9]+:    66 0f 55 ee             andnpd %xmm6,%xmm5
+[      ]*[a-f0-9]+:    66 0f 54 37             andpd  \(%edi\),%xmm6
+[      ]*[a-f0-9]+:    66 0f 54 f8             andpd  %xmm0,%xmm7
+[      ]*[a-f0-9]+:    66 0f c2 c1 02          cmplepd %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f c2 0a 03          cmpunordpd \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    f2 0f c2 d2 04          cmpneqsd %xmm2,%xmm2
+[      ]*[a-f0-9]+:    f2 0f c2 1c 24 05       cmpnltsd \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    66 0f c2 e5 06          cmpnlepd %xmm5,%xmm4
+[      ]*[a-f0-9]+:    66 0f c2 2e 07          cmpordpd \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    f2 0f c2 f7 00          cmpeqsd %xmm7,%xmm6
+[      ]*[a-f0-9]+:    f2 0f c2 38 01          cmpltsd \(%eax\),%xmm7
+[      ]*[a-f0-9]+:    66 0f c2 c1 00          cmpeqpd %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f c2 0a 00          cmpeqpd \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    f2 0f c2 d2 00          cmpeqsd %xmm2,%xmm2
+[      ]*[a-f0-9]+:    f2 0f c2 1c 24 00       cmpeqsd \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    66 0f c2 e5 01          cmpltpd %xmm5,%xmm4
+[      ]*[a-f0-9]+:    66 0f c2 2e 01          cmpltpd \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    f2 0f c2 f7 01          cmpltsd %xmm7,%xmm6
+[      ]*[a-f0-9]+:    f2 0f c2 38 01          cmpltsd \(%eax\),%xmm7
+[      ]*[a-f0-9]+:    66 0f c2 01 02          cmplepd \(%ecx\),%xmm0
+[      ]*[a-f0-9]+:    66 0f c2 ca 02          cmplepd %xmm2,%xmm1
+[      ]*[a-f0-9]+:    f2 0f c2 13 02          cmplesd \(%ebx\),%xmm2
+[      ]*[a-f0-9]+:    f2 0f c2 dc 02          cmplesd %xmm4,%xmm3
+[      ]*[a-f0-9]+:    66 0f c2 65 00 03       cmpunordpd 0x0\(%ebp\),%xmm4
+[      ]*[a-f0-9]+:    66 0f c2 ee 03          cmpunordpd %xmm6,%xmm5
+[      ]*[a-f0-9]+:    f2 0f c2 37 03          cmpunordsd \(%edi\),%xmm6
+[      ]*[a-f0-9]+:    f2 0f c2 f8 03          cmpunordsd %xmm0,%xmm7
+[      ]*[a-f0-9]+:    66 0f c2 c1 04          cmpneqpd %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f c2 0a 04          cmpneqpd \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    f2 0f c2 d2 04          cmpneqsd %xmm2,%xmm2
+[      ]*[a-f0-9]+:    f2 0f c2 1c 24 04       cmpneqsd \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    66 0f c2 e5 05          cmpnltpd %xmm5,%xmm4
+[      ]*[a-f0-9]+:    66 0f c2 2e 05          cmpnltpd \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    f2 0f c2 f7 05          cmpnltsd %xmm7,%xmm6
+[      ]*[a-f0-9]+:    f2 0f c2 38 05          cmpnltsd \(%eax\),%xmm7
+[      ]*[a-f0-9]+:    66 0f c2 01 06          cmpnlepd \(%ecx\),%xmm0
+[      ]*[a-f0-9]+:    66 0f c2 ca 06          cmpnlepd %xmm2,%xmm1
+[      ]*[a-f0-9]+:    f2 0f c2 13 06          cmpnlesd \(%ebx\),%xmm2
+[      ]*[a-f0-9]+:    f2 0f c2 dc 06          cmpnlesd %xmm4,%xmm3
+[      ]*[a-f0-9]+:    66 0f c2 65 00 07       cmpordpd 0x0\(%ebp\),%xmm4
+[      ]*[a-f0-9]+:    66 0f c2 ee 07          cmpordpd %xmm6,%xmm5
+[      ]*[a-f0-9]+:    f2 0f c2 37 07          cmpordsd \(%edi\),%xmm6
+[      ]*[a-f0-9]+:    f2 0f c2 f8 07          cmpordsd %xmm0,%xmm7
+[      ]*[a-f0-9]+:    66 0f 2f c1             comisd %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 2f 0a             comisd \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    66 0f 2a d3             cvtpi2pd %mm3,%xmm2
+[      ]*[a-f0-9]+:    66 0f 2a 1c 24          cvtpi2pd \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    f2 0f 2a e5             cvtsi2sd %ebp,%xmm4
+[      ]*[a-f0-9]+:    f2 0f 2a 2e             cvtsi2sdl \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    66 0f 2d f7             cvtpd2pi %xmm7,%mm6
+[      ]*[a-f0-9]+:    66 0f 2d 38             cvtpd2pi \(%eax\),%mm7
+[      ]*[a-f0-9]+:    f2 0f 2d 01             cvtsd2si \(%ecx\),%eax
+[      ]*[a-f0-9]+:    f2 0f 2d ca             cvtsd2si %xmm2,%ecx
+[      ]*[a-f0-9]+:    66 0f 2c 13             cvttpd2pi \(%ebx\),%mm2
+[      ]*[a-f0-9]+:    66 0f 2c dc             cvttpd2pi %xmm4,%mm3
+[      ]*[a-f0-9]+:    f2 0f 2c 65 00          cvttsd2si 0x0\(%ebp\),%esp
+[      ]*[a-f0-9]+:    f2 0f 2c ee             cvttsd2si %xmm6,%ebp
+[      ]*[a-f0-9]+:    66 0f 5e c1             divpd  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 5e 0a             divpd  \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    f2 0f 5e d3             divsd  %xmm3,%xmm2
+[      ]*[a-f0-9]+:    f2 0f 5e 1c 24          divsd  \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    0f ae 55 00             ldmxcsr 0x0\(%ebp\)
+[      ]*[a-f0-9]+:    0f ae 1e                stmxcsr \(%esi\)
+[      ]*[a-f0-9]+:    0f ae f8                sfence 
+[      ]*[a-f0-9]+:    66 0f 5f c1             maxpd  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 5f 0a             maxpd  \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    f2 0f 5f d3             maxsd  %xmm3,%xmm2
+[      ]*[a-f0-9]+:    f2 0f 5f 1c 24          maxsd  \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    66 0f 5d e5             minpd  %xmm5,%xmm4
+[      ]*[a-f0-9]+:    66 0f 5d 2e             minpd  \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    f2 0f 5d f7             minsd  %xmm7,%xmm6
+[      ]*[a-f0-9]+:    f2 0f 5d 38             minsd  \(%eax\),%xmm7
+[      ]*[a-f0-9]+:    66 0f 28 c1             movapd %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 29 11             movapd %xmm2,\(%ecx\)
+[      ]*[a-f0-9]+:    66 0f 28 12             movapd \(%edx\),%xmm2
+[      ]*[a-f0-9]+:    66 0f 17 2c 24          movhpd %xmm5,\(%esp\)
+[      ]*[a-f0-9]+:    66 0f 16 2e             movhpd \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    66 0f 13 07             movlpd %xmm0,\(%edi\)
+[      ]*[a-f0-9]+:    66 0f 12 00             movlpd \(%eax\),%xmm0
+[      ]*[a-f0-9]+:    66 0f 50 ca             movmskpd %xmm2,%ecx
+[      ]*[a-f0-9]+:    66 0f 10 d3             movupd %xmm3,%xmm2
+[      ]*[a-f0-9]+:    66 0f 11 22             movupd %xmm4,\(%edx\)
+[      ]*[a-f0-9]+:    66 0f 10 65 00          movupd 0x0\(%ebp\),%xmm4
+[      ]*[a-f0-9]+:    f2 0f 10 ee             movsd  %xmm6,%xmm5
+[      ]*[a-f0-9]+:    f2 0f 11 3e             movsd  %xmm7,\(%esi\)
+[      ]*[a-f0-9]+:    f2 0f 10 38             movsd  \(%eax\),%xmm7
+[      ]*[a-f0-9]+:    66 0f 59 c1             mulpd  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 59 0a             mulpd  \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    f2 0f 59 d2             mulsd  %xmm2,%xmm2
+[      ]*[a-f0-9]+:    f2 0f 59 1c 24          mulsd  \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    66 0f 56 e5             orpd   %xmm5,%xmm4
+[      ]*[a-f0-9]+:    66 0f 56 2e             orpd   \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    66 0f c6 37 02          shufpd \$0x2,\(%edi\),%xmm6
+[      ]*[a-f0-9]+:    66 0f c6 f8 03          shufpd \$0x3,%xmm0,%xmm7
+[      ]*[a-f0-9]+:    66 0f 51 c1             sqrtpd %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 51 0a             sqrtpd \(%edx\),%xmm1
+[      ]*[a-f0-9]+:    f2 0f 51 d2             sqrtsd %xmm2,%xmm2
+[      ]*[a-f0-9]+:    f2 0f 51 1c 24          sqrtsd \(%esp\),%xmm3
+[      ]*[a-f0-9]+:    66 0f 5c e5             subpd  %xmm5,%xmm4
+[      ]*[a-f0-9]+:    66 0f 5c 2e             subpd  \(%esi\),%xmm5
+[      ]*[a-f0-9]+:    f2 0f 5c f7             subsd  %xmm7,%xmm6
+[      ]*[a-f0-9]+:    f2 0f 5c 38             subsd  \(%eax\),%xmm7
+[      ]*[a-f0-9]+:    66 0f 2e 01             ucomisd \(%ecx\),%xmm0
+[      ]*[a-f0-9]+:    66 0f 2e ca             ucomisd %xmm2,%xmm1
+[      ]*[a-f0-9]+:    66 0f 15 13             unpckhpd \(%ebx\),%xmm2
+[      ]*[a-f0-9]+:    66 0f 15 dc             unpckhpd %xmm4,%xmm3
+[      ]*[a-f0-9]+:    66 0f 14 65 00          unpcklpd 0x0\(%ebp\),%xmm4
+[      ]*[a-f0-9]+:    66 0f 14 ee             unpcklpd %xmm6,%xmm5
+[      ]*[a-f0-9]+:    66 0f 57 37             xorpd  \(%edi\),%xmm6
+[      ]*[a-f0-9]+:    66 0f 57 f8             xorpd  %xmm0,%xmm7
+[      ]*[a-f0-9]+:    66 0f 2b 33             movntpd %xmm6,\(%ebx\)
+[      ]*[a-f0-9]+:    66 0f 57 c8             xorpd  %xmm0,%xmm1
+[      ]*[a-f0-9]+:    f3 0f e6 c8             cvtdq2pd %xmm0,%xmm1
+[      ]*[a-f0-9]+:    f2 0f e6 c8             cvtpd2dq %xmm0,%xmm1
+[      ]*[a-f0-9]+:    0f 5b c8                cvtdq2ps %xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f 5a c8             cvtpd2ps %xmm0,%xmm1
+[      ]*[a-f0-9]+:    0f 5a c8                cvtps2pd %xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f 5b c8             cvtps2dq %xmm0,%xmm1
+[      ]*[a-f0-9]+:    f2 0f 5a c8             cvtsd2ss %xmm0,%xmm1
+[      ]*[a-f0-9]+:    f3 0f 5a c8             cvtss2sd %xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f e6 c8             cvttpd2dq %xmm0,%xmm1
+[      ]*[a-f0-9]+:    f3 0f 5b c8             cvttps2dq %xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f f7 c8             maskmovdqu %xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f 6f c8             movdqa %xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f 7f 06             movdqa %xmm0,\(%esi\)
+[      ]*[a-f0-9]+:    f3 0f 6f c8             movdqu %xmm0,%xmm1
+[      ]*[a-f0-9]+:    f3 0f 7f 06             movdqu %xmm0,\(%esi\)
+[      ]*[a-f0-9]+:    f2 0f d6 c8             movdq2q %xmm0,%mm1
+[      ]*[a-f0-9]+:    f3 0f d6 c8             movq2dq %mm0,%xmm1
+[      ]*[a-f0-9]+:    0f f4 c8                pmuludq %mm0,%mm1
+[      ]*[a-f0-9]+:    0f f4 08                pmuludq \(%eax\),%mm1
+[      ]*[a-f0-9]+:    66 0f f4 c8             pmuludq %xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f f4 08             pmuludq \(%eax\),%xmm1
+[      ]*[a-f0-9]+:    66 0f 70 c8 01          pshufd \$0x1,%xmm0,%xmm1
+[      ]*[a-f0-9]+:    f3 0f 70 c8 01          pshufhw \$0x1,%xmm0,%xmm1
+[      ]*[a-f0-9]+:    f2 0f 70 c8 01          pshuflw \$0x1,%xmm0,%xmm1
+[      ]*[a-f0-9]+:    66 0f 73 f8 01          pslldq \$0x1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 73 d8 01          psrldq \$0x1,%xmm0
+[      ]*[a-f0-9]+:    66 0f 6d c8             punpckhqdq %xmm0,%xmm1
+[      ]*[a-f0-9]+:    0f d4 c1                paddq  %mm1,%mm0
+[      ]*[a-f0-9]+:    0f d4 00                paddq  \(%eax\),%mm0
+[      ]*[a-f0-9]+:    66 0f d4 c1             paddq  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f d4 00             paddq  \(%eax\),%xmm0
+[      ]*[a-f0-9]+:    0f fb c1                psubq  %mm1,%mm0
+[      ]*[a-f0-9]+:    0f fb 00                psubq  \(%eax\),%mm0
+[      ]*[a-f0-9]+:    66 0f fb c1             psubq  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f fb 00             psubq  \(%eax\),%xmm0
+#pass
index edb79fc..c6375dc 100644 (file)
@@ -137,13 +137,21 @@ foo:
        movdqu          %xmm0, (%esi)
        movdq2q         %xmm0, %mm1
        movq2dq         %mm0, %xmm1
+       pmuludq         %mm0, %mm1
+       pmuludq         (%eax), %mm1
        pmuludq         %xmm0, %xmm1
-       pmuludq         %xmm0, %xmm1
+       pmuludq         (%eax), %xmm1
        pshufd          $1, %xmm0, %xmm1
        pshufhw         $1, %xmm0, %xmm1
        pshuflw         $1, %xmm0, %xmm1
        pslldq          $1, %xmm0
        psrldq          $1, %xmm0
        punpckhqdq      %xmm0, %xmm1
-
- .p2align 4
+       paddq           %mm1,%mm0
+       paddq           (%eax),%mm0
+       paddq           %xmm1,%xmm0
+       paddq           (%eax),%xmm0
+       psubq           %mm1,%mm0
+       psubq           (%eax),%mm0
+       psubq           %xmm1,%xmm0
+       psubq           (%eax),%xmm0
index 53efdbc..0322a96 100644 (file)
@@ -113,13 +113,25 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f3 0f c2 38 10          cmpss  xmm7,DWORD PTR \[rax\],0x10
 [      ]*[a-f0-9]+:    f2 0f c2 f7 10          cmpsd  xmm6,xmm7,0x10
 [      ]*[a-f0-9]+:    f2 0f c2 38 10          cmpsd  xmm7,QWORD PTR \[rax\],0x10
-[      ]*[a-f0-9]+:    f2 0f d0 0d 78 56 34 12         addsubps xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123458be <_start\+0x123458be>
-[      ]*[a-f0-9]+:    66 0f 2f 0d 78 56 34 12         comisd xmm1,QWORD PTR \[rip\+0x12345678\]        # 123458c6 <_start\+0x123458c6>
-[      ]*[a-f0-9]+:    0f 2f 0d 78 56 34 12    comiss xmm1,DWORD PTR \[rip\+0x12345678\]        # 123458cd <_start\+0x123458cd>
-[      ]*[a-f0-9]+:    f3 0f e6 0d 78 56 34 12         cvtdq2pd xmm1,QWORD PTR \[rip\+0x12345678\]        # 123458d5 <_start\+0x123458d5>
-[      ]*[a-f0-9]+:    f2 0f e6 0d 78 56 34 12         cvtpd2dq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123458dd <_start\+0x123458dd>
-[      ]*[a-f0-9]+:    0f 5a 0d 78 56 34 12    cvtps2pd xmm1,QWORD PTR \[rip\+0x12345678\]        # 123458e4 <_start\+0x123458e4>
-[      ]*[a-f0-9]+:    f3 0f 5b 0d 78 56 34 12         cvttps2dq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123458ec <_start\+0x123458ec>
+[      ]*[a-f0-9]+:    0f d4 c1                paddq  mm0,mm1
+[      ]*[a-f0-9]+:    0f d4 00                paddq  mm0,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f d4 c1             paddq  xmm0,xmm1
+[      ]*[a-f0-9]+:    66 0f d4 00             paddq  xmm0,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    0f fb c1                psubq  mm0,mm1
+[      ]*[a-f0-9]+:    0f fb 00                psubq  mm0,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f fb c1             psubq  xmm0,xmm1
+[      ]*[a-f0-9]+:    66 0f fb 00             psubq  xmm0,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    0f f4 c1                pmuludq mm0,mm1
+[      ]*[a-f0-9]+:    0f f4 00                pmuludq mm0,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f f4 c1             pmuludq xmm0,xmm1
+[      ]*[a-f0-9]+:    66 0f f4 00             pmuludq xmm0,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    f2 0f d0 0d 78 56 34 12         addsubps xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123458e8 <_start\+0x123458e8>
+[      ]*[a-f0-9]+:    66 0f 2f 0d 78 56 34 12         comisd xmm1,QWORD PTR \[rip\+0x12345678\]        # 123458f0 <_start\+0x123458f0>
+[      ]*[a-f0-9]+:    0f 2f 0d 78 56 34 12    comiss xmm1,DWORD PTR \[rip\+0x12345678\]        # 123458f7 <_start\+0x123458f7>
+[      ]*[a-f0-9]+:    f3 0f e6 0d 78 56 34 12         cvtdq2pd xmm1,QWORD PTR \[rip\+0x12345678\]        # 123458ff <_start\+0x123458ff>
+[      ]*[a-f0-9]+:    f2 0f e6 0d 78 56 34 12         cvtpd2dq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345907 <_start\+0x12345907>
+[      ]*[a-f0-9]+:    0f 5a 0d 78 56 34 12    cvtps2pd xmm1,QWORD PTR \[rip\+0x12345678\]        # 1234590e <_start\+0x1234590e>
+[      ]*[a-f0-9]+:    f3 0f 5b 0d 78 56 34 12         cvttps2dq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345916 <_start\+0x12345916>
 [      ]*[a-f0-9]+:    f3 0f 2a c8             cvtsi2ss xmm1,eax
 [      ]*[a-f0-9]+:    f2 0f 2a c8             cvtsi2sd xmm1,eax
 [      ]*[a-f0-9]+:    f3 0f 2a c8             cvtsi2ss xmm1,eax
@@ -136,32 +148,32 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f2 48 0f 2a 08          cvtsi2sd xmm1,QWORD PTR \[rax\]
 [      ]*[a-f0-9]+:    f3 48 0f 2a 08          cvtsi2ss xmm1,QWORD PTR \[rax\]
 [      ]*[a-f0-9]+:    f2 48 0f 2a 08          cvtsi2sd xmm1,QWORD PTR \[rax\]
-[      ]*[a-f0-9]+:    f2 0f 7c 0d 78 56 34 12         haddps xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 1234593c <_start\+0x1234593c>
-[      ]*[a-f0-9]+:    f3 0f 7f 0d 78 56 34 12         movdqu XMMWORD PTR \[rip\+0x12345678\],xmm1        # 12345944 <_start\+0x12345944>
-[      ]*[a-f0-9]+:    f3 0f 6f 0d 78 56 34 12         movdqu xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 1234594c <_start\+0x1234594c>
-[      ]*[a-f0-9]+:    66 0f 17 0d 78 56 34 12         movhpd QWORD PTR \[rip\+0x12345678\],xmm1        # 12345954 <_start\+0x12345954>
-[      ]*[a-f0-9]+:    66 0f 16 0d 78 56 34 12         movhpd xmm1,QWORD PTR \[rip\+0x12345678\]        # 1234595c <_start\+0x1234595c>
-[      ]*[a-f0-9]+:    0f 17 0d 78 56 34 12    movhps QWORD PTR \[rip\+0x12345678\],xmm1        # 12345963 <_start\+0x12345963>
-[      ]*[a-f0-9]+:    0f 16 0d 78 56 34 12    movhps xmm1,QWORD PTR \[rip\+0x12345678\]        # 1234596a <_start\+0x1234596a>
-[      ]*[a-f0-9]+:    66 0f 13 0d 78 56 34 12         movlpd QWORD PTR \[rip\+0x12345678\],xmm1        # 12345972 <_start\+0x12345972>
-[      ]*[a-f0-9]+:    66 0f 12 0d 78 56 34 12         movlpd xmm1,QWORD PTR \[rip\+0x12345678\]        # 1234597a <_start\+0x1234597a>
-[      ]*[a-f0-9]+:    0f 13 0d 78 56 34 12    movlps QWORD PTR \[rip\+0x12345678\],xmm1        # 12345981 <_start\+0x12345981>
-[      ]*[a-f0-9]+:    0f 12 0d 78 56 34 12    movlps xmm1,QWORD PTR \[rip\+0x12345678\]        # 12345988 <_start\+0x12345988>
-[      ]*[a-f0-9]+:    66 0f d6 0d 78 56 34 12         movq   QWORD PTR \[rip\+0x12345678\],xmm1        # 12345990 <_start\+0x12345990>
-[      ]*[a-f0-9]+:    f3 0f 7e 0d 78 56 34 12         movq   xmm1,QWORD PTR \[rip\+0x12345678\]        # 12345998 <_start\+0x12345998>
-[      ]*[a-f0-9]+:    f3 0f 16 0d 78 56 34 12         movshdup xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459a0 <_start\+0x123459a0>
-[      ]*[a-f0-9]+:    f3 0f 12 0d 78 56 34 12         movsldup xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459a8 <_start\+0x123459a8>
-[      ]*[a-f0-9]+:    f3 0f 70 0d 78 56 34 12 90      pshufhw xmm1,XMMWORD PTR \[rip\+0x12345678\],0x90        # 123459b1 <_start\+0x123459b1>
-[      ]*[a-f0-9]+:    f2 0f 70 0d 78 56 34 12 90      pshuflw xmm1,XMMWORD PTR \[rip\+0x12345678\],0x90        # 123459ba <_start\+0x123459ba>
-[      ]*[a-f0-9]+:    0f 60 0d 78 56 34 12    punpcklbw mm1,DWORD PTR \[rip\+0x12345678\]        # 123459c1 <_start\+0x123459c1>
-[      ]*[a-f0-9]+:    0f 62 0d 78 56 34 12    punpckldq mm1,DWORD PTR \[rip\+0x12345678\]        # 123459c8 <_start\+0x123459c8>
-[      ]*[a-f0-9]+:    0f 61 0d 78 56 34 12    punpcklwd mm1,DWORD PTR \[rip\+0x12345678\]        # 123459cf <_start\+0x123459cf>
-[      ]*[a-f0-9]+:    66 0f 60 0d 78 56 34 12         punpcklbw xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459d7 <_start\+0x123459d7>
-[      ]*[a-f0-9]+:    66 0f 62 0d 78 56 34 12         punpckldq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459df <_start\+0x123459df>
-[      ]*[a-f0-9]+:    66 0f 61 0d 78 56 34 12         punpcklwd xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459e7 <_start\+0x123459e7>
-[      ]*[a-f0-9]+:    66 0f 6c 0d 78 56 34 12         punpcklqdq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459ef <_start\+0x123459ef>
-[      ]*[a-f0-9]+:    66 0f 2e 0d 78 56 34 12         ucomisd xmm1,QWORD PTR \[rip\+0x12345678\]        # 123459f7 <_start\+0x123459f7>
-[      ]*[a-f0-9]+:    0f 2e 0d 78 56 34 12    ucomiss xmm1,DWORD PTR \[rip\+0x12345678\]        # 123459fe <_start\+0x123459fe>
+[      ]*[a-f0-9]+:    f2 0f 7c 0d 78 56 34 12         haddps xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345966 <_start\+0x12345966>
+[      ]*[a-f0-9]+:    f3 0f 7f 0d 78 56 34 12         movdqu XMMWORD PTR \[rip\+0x12345678\],xmm1        # 1234596e <_start\+0x1234596e>
+[      ]*[a-f0-9]+:    f3 0f 6f 0d 78 56 34 12         movdqu xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345976 <_start\+0x12345976>
+[      ]*[a-f0-9]+:    66 0f 17 0d 78 56 34 12         movhpd QWORD PTR \[rip\+0x12345678\],xmm1        # 1234597e <_start\+0x1234597e>
+[      ]*[a-f0-9]+:    66 0f 16 0d 78 56 34 12         movhpd xmm1,QWORD PTR \[rip\+0x12345678\]        # 12345986 <_start\+0x12345986>
+[      ]*[a-f0-9]+:    0f 17 0d 78 56 34 12    movhps QWORD PTR \[rip\+0x12345678\],xmm1        # 1234598d <_start\+0x1234598d>
+[      ]*[a-f0-9]+:    0f 16 0d 78 56 34 12    movhps xmm1,QWORD PTR \[rip\+0x12345678\]        # 12345994 <_start\+0x12345994>
+[      ]*[a-f0-9]+:    66 0f 13 0d 78 56 34 12         movlpd QWORD PTR \[rip\+0x12345678\],xmm1        # 1234599c <_start\+0x1234599c>
+[      ]*[a-f0-9]+:    66 0f 12 0d 78 56 34 12         movlpd xmm1,QWORD PTR \[rip\+0x12345678\]        # 123459a4 <_start\+0x123459a4>
+[      ]*[a-f0-9]+:    0f 13 0d 78 56 34 12    movlps QWORD PTR \[rip\+0x12345678\],xmm1        # 123459ab <_start\+0x123459ab>
+[      ]*[a-f0-9]+:    0f 12 0d 78 56 34 12    movlps xmm1,QWORD PTR \[rip\+0x12345678\]        # 123459b2 <_start\+0x123459b2>
+[      ]*[a-f0-9]+:    66 0f d6 0d 78 56 34 12         movq   QWORD PTR \[rip\+0x12345678\],xmm1        # 123459ba <_start\+0x123459ba>
+[      ]*[a-f0-9]+:    f3 0f 7e 0d 78 56 34 12         movq   xmm1,QWORD PTR \[rip\+0x12345678\]        # 123459c2 <_start\+0x123459c2>
+[      ]*[a-f0-9]+:    f3 0f 16 0d 78 56 34 12         movshdup xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459ca <_start\+0x123459ca>
+[      ]*[a-f0-9]+:    f3 0f 12 0d 78 56 34 12         movsldup xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 123459d2 <_start\+0x123459d2>
+[      ]*[a-f0-9]+:    f3 0f 70 0d 78 56 34 12 90      pshufhw xmm1,XMMWORD PTR \[rip\+0x12345678\],0x90        # 123459db <_start\+0x123459db>
+[      ]*[a-f0-9]+:    f2 0f 70 0d 78 56 34 12 90      pshuflw xmm1,XMMWORD PTR \[rip\+0x12345678\],0x90        # 123459e4 <_start\+0x123459e4>
+[      ]*[a-f0-9]+:    0f 60 0d 78 56 34 12    punpcklbw mm1,DWORD PTR \[rip\+0x12345678\]        # 123459eb <_start\+0x123459eb>
+[      ]*[a-f0-9]+:    0f 62 0d 78 56 34 12    punpckldq mm1,DWORD PTR \[rip\+0x12345678\]        # 123459f2 <_start\+0x123459f2>
+[      ]*[a-f0-9]+:    0f 61 0d 78 56 34 12    punpcklwd mm1,DWORD PTR \[rip\+0x12345678\]        # 123459f9 <_start\+0x123459f9>
+[      ]*[a-f0-9]+:    66 0f 60 0d 78 56 34 12         punpcklbw xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345a01 <_start\+0x12345a01>
+[      ]*[a-f0-9]+:    66 0f 62 0d 78 56 34 12         punpckldq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345a09 <_start\+0x12345a09>
+[      ]*[a-f0-9]+:    66 0f 61 0d 78 56 34 12         punpcklwd xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345a11 <_start\+0x12345a11>
+[      ]*[a-f0-9]+:    66 0f 6c 0d 78 56 34 12         punpcklqdq xmm1,XMMWORD PTR \[rip\+0x12345678\]        # 12345a19 <_start\+0x12345a19>
+[      ]*[a-f0-9]+:    66 0f 2e 0d 78 56 34 12         ucomisd xmm1,QWORD PTR \[rip\+0x12345678\]        # 12345a21 <_start\+0x12345a21>
+[      ]*[a-f0-9]+:    0f 2e 0d 78 56 34 12    ucomiss xmm1,DWORD PTR \[rip\+0x12345678\]        # 12345a28 <_start\+0x12345a28>
 [      ]*[a-f0-9]+:    f2 0f c2 00 00          cmpeqsd xmm0,QWORD PTR \[rax\]
 [      ]*[a-f0-9]+:    f3 0f c2 00 00          cmpeqss xmm0,DWORD PTR \[rax\]
 [      ]*[a-f0-9]+:    66 0f 2a 00             cvtpi2pd xmm0,QWORD PTR \[rax\]
@@ -220,4 +232,16 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f3 0f c2 38 10          cmpss  xmm7,DWORD PTR \[rax\],0x10
 [      ]*[a-f0-9]+:    f2 0f c2 f7 10          cmpsd  xmm6,xmm7,0x10
 [      ]*[a-f0-9]+:    f2 0f c2 38 10          cmpsd  xmm7,QWORD PTR \[rax\],0x10
+[      ]*[a-f0-9]+:    0f d4 08                paddq  mm1,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    0f d4 08                paddq  mm1,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f d4 08             paddq  xmm1,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f d4 08             paddq  xmm1,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    0f fb 08                psubq  mm1,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    0f fb 08                psubq  mm1,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f fb 08             psubq  xmm1,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f fb 08             psubq  xmm1,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    0f f4 08                pmuludq mm1,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    0f f4 08                pmuludq mm1,QWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f f4 08             pmuludq xmm1,XMMWORD PTR \[rax\]
+[      ]*[a-f0-9]+:    66 0f f4 08             pmuludq xmm1,XMMWORD PTR \[rax\]
 #pass
index f5be3b9..e4431e0 100644 (file)
@@ -113,13 +113,25 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f3 0f c2 38 10          cmpss  \$0x10,\(%rax\),%xmm7
 [      ]*[a-f0-9]+:    f2 0f c2 f7 10          cmpsd  \$0x10,%xmm7,%xmm6
 [      ]*[a-f0-9]+:    f2 0f c2 38 10          cmpsd  \$0x10,\(%rax\),%xmm7
-[      ]*[a-f0-9]+:    f2 0f d0 0d 78 56 34 12         addsubps 0x12345678\(%rip\),%xmm1        # 123458be <_start\+0x123458be>
-[      ]*[a-f0-9]+:    66 0f 2f 0d 78 56 34 12         comisd 0x12345678\(%rip\),%xmm1        # 123458c6 <_start\+0x123458c6>
-[      ]*[a-f0-9]+:    0f 2f 0d 78 56 34 12    comiss 0x12345678\(%rip\),%xmm1        # 123458cd <_start\+0x123458cd>
-[      ]*[a-f0-9]+:    f3 0f e6 0d 78 56 34 12         cvtdq2pd 0x12345678\(%rip\),%xmm1        # 123458d5 <_start\+0x123458d5>
-[      ]*[a-f0-9]+:    f2 0f e6 0d 78 56 34 12         cvtpd2dq 0x12345678\(%rip\),%xmm1        # 123458dd <_start\+0x123458dd>
-[      ]*[a-f0-9]+:    0f 5a 0d 78 56 34 12    cvtps2pd 0x12345678\(%rip\),%xmm1        # 123458e4 <_start\+0x123458e4>
-[      ]*[a-f0-9]+:    f3 0f 5b 0d 78 56 34 12         cvttps2dq 0x12345678\(%rip\),%xmm1        # 123458ec <_start\+0x123458ec>
+[      ]*[a-f0-9]+:    0f d4 c1                paddq  %mm1,%mm0
+[      ]*[a-f0-9]+:    0f d4 00                paddq  \(%rax\),%mm0
+[      ]*[a-f0-9]+:    66 0f d4 c1             paddq  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f d4 00             paddq  \(%rax\),%xmm0
+[      ]*[a-f0-9]+:    0f fb c1                psubq  %mm1,%mm0
+[      ]*[a-f0-9]+:    0f fb 00                psubq  \(%rax\),%mm0
+[      ]*[a-f0-9]+:    66 0f fb c1             psubq  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f fb 00             psubq  \(%rax\),%xmm0
+[      ]*[a-f0-9]+:    0f f4 c1                pmuludq %mm1,%mm0
+[      ]*[a-f0-9]+:    0f f4 00                pmuludq \(%rax\),%mm0
+[      ]*[a-f0-9]+:    66 0f f4 c1             pmuludq %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f f4 00             pmuludq \(%rax\),%xmm0
+[      ]*[a-f0-9]+:    f2 0f d0 0d 78 56 34 12         addsubps 0x12345678\(%rip\),%xmm1        # 123458e8 <_start\+0x123458e8>
+[      ]*[a-f0-9]+:    66 0f 2f 0d 78 56 34 12         comisd 0x12345678\(%rip\),%xmm1        # 123458f0 <_start\+0x123458f0>
+[      ]*[a-f0-9]+:    0f 2f 0d 78 56 34 12    comiss 0x12345678\(%rip\),%xmm1        # 123458f7 <_start\+0x123458f7>
+[      ]*[a-f0-9]+:    f3 0f e6 0d 78 56 34 12         cvtdq2pd 0x12345678\(%rip\),%xmm1        # 123458ff <_start\+0x123458ff>
+[      ]*[a-f0-9]+:    f2 0f e6 0d 78 56 34 12         cvtpd2dq 0x12345678\(%rip\),%xmm1        # 12345907 <_start\+0x12345907>
+[      ]*[a-f0-9]+:    0f 5a 0d 78 56 34 12    cvtps2pd 0x12345678\(%rip\),%xmm1        # 1234590e <_start\+0x1234590e>
+[      ]*[a-f0-9]+:    f3 0f 5b 0d 78 56 34 12         cvttps2dq 0x12345678\(%rip\),%xmm1        # 12345916 <_start\+0x12345916>
 [      ]*[a-f0-9]+:    f3 0f 2a c8             cvtsi2ssl %eax,%xmm1
 [      ]*[a-f0-9]+:    f2 0f 2a c8             cvtsi2sdl %eax,%xmm1
 [      ]*[a-f0-9]+:    f3 0f 2a c8             cvtsi2ssl %eax,%xmm1
@@ -136,32 +148,32 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f2 48 0f 2a 08          cvtsi2sdq \(%rax\),%xmm1
 [      ]*[a-f0-9]+:    f3 48 0f 2a 08          cvtsi2ssq \(%rax\),%xmm1
 [      ]*[a-f0-9]+:    f2 48 0f 2a 08          cvtsi2sdq \(%rax\),%xmm1
-[      ]*[a-f0-9]+:    f2 0f 7c 0d 78 56 34 12         haddps 0x12345678\(%rip\),%xmm1        # 1234593c <_start\+0x1234593c>
-[      ]*[a-f0-9]+:    f3 0f 7f 0d 78 56 34 12         movdqu %xmm1,0x12345678\(%rip\)        # 12345944 <_start\+0x12345944>
-[      ]*[a-f0-9]+:    f3 0f 6f 0d 78 56 34 12         movdqu 0x12345678\(%rip\),%xmm1        # 1234594c <_start\+0x1234594c>
-[      ]*[a-f0-9]+:    66 0f 17 0d 78 56 34 12         movhpd %xmm1,0x12345678\(%rip\)        # 12345954 <_start\+0x12345954>
-[      ]*[a-f0-9]+:    66 0f 16 0d 78 56 34 12         movhpd 0x12345678\(%rip\),%xmm1        # 1234595c <_start\+0x1234595c>
-[      ]*[a-f0-9]+:    0f 17 0d 78 56 34 12    movhps %xmm1,0x12345678\(%rip\)        # 12345963 <_start\+0x12345963>
-[      ]*[a-f0-9]+:    0f 16 0d 78 56 34 12    movhps 0x12345678\(%rip\),%xmm1        # 1234596a <_start\+0x1234596a>
-[      ]*[a-f0-9]+:    66 0f 13 0d 78 56 34 12         movlpd %xmm1,0x12345678\(%rip\)        # 12345972 <_start\+0x12345972>
-[      ]*[a-f0-9]+:    66 0f 12 0d 78 56 34 12         movlpd 0x12345678\(%rip\),%xmm1        # 1234597a <_start\+0x1234597a>
-[      ]*[a-f0-9]+:    0f 13 0d 78 56 34 12    movlps %xmm1,0x12345678\(%rip\)        # 12345981 <_start\+0x12345981>
-[      ]*[a-f0-9]+:    0f 12 0d 78 56 34 12    movlps 0x12345678\(%rip\),%xmm1        # 12345988 <_start\+0x12345988>
-[      ]*[a-f0-9]+:    66 0f d6 0d 78 56 34 12         movq   %xmm1,0x12345678\(%rip\)        # 12345990 <_start\+0x12345990>
-[      ]*[a-f0-9]+:    f3 0f 7e 0d 78 56 34 12         movq   0x12345678\(%rip\),%xmm1        # 12345998 <_start\+0x12345998>
-[      ]*[a-f0-9]+:    f3 0f 16 0d 78 56 34 12         movshdup 0x12345678\(%rip\),%xmm1        # 123459a0 <_start\+0x123459a0>
-[      ]*[a-f0-9]+:    f3 0f 12 0d 78 56 34 12         movsldup 0x12345678\(%rip\),%xmm1        # 123459a8 <_start\+0x123459a8>
-[      ]*[a-f0-9]+:    f3 0f 70 0d 78 56 34 12 90      pshufhw \$0x90,0x12345678\(%rip\),%xmm1        # 123459b1 <_start\+0x123459b1>
-[      ]*[a-f0-9]+:    f2 0f 70 0d 78 56 34 12 90      pshuflw \$0x90,0x12345678\(%rip\),%xmm1        # 123459ba <_start\+0x123459ba>
-[      ]*[a-f0-9]+:    0f 60 0d 78 56 34 12    punpcklbw 0x12345678\(%rip\),%mm1        # 123459c1 <_start\+0x123459c1>
-[      ]*[a-f0-9]+:    0f 62 0d 78 56 34 12    punpckldq 0x12345678\(%rip\),%mm1        # 123459c8 <_start\+0x123459c8>
-[      ]*[a-f0-9]+:    0f 61 0d 78 56 34 12    punpcklwd 0x12345678\(%rip\),%mm1        # 123459cf <_start\+0x123459cf>
-[      ]*[a-f0-9]+:    66 0f 60 0d 78 56 34 12         punpcklbw 0x12345678\(%rip\),%xmm1        # 123459d7 <_start\+0x123459d7>
-[      ]*[a-f0-9]+:    66 0f 62 0d 78 56 34 12         punpckldq 0x12345678\(%rip\),%xmm1        # 123459df <_start\+0x123459df>
-[      ]*[a-f0-9]+:    66 0f 61 0d 78 56 34 12         punpcklwd 0x12345678\(%rip\),%xmm1        # 123459e7 <_start\+0x123459e7>
-[      ]*[a-f0-9]+:    66 0f 6c 0d 78 56 34 12         punpcklqdq 0x12345678\(%rip\),%xmm1        # 123459ef <_start\+0x123459ef>
-[      ]*[a-f0-9]+:    66 0f 2e 0d 78 56 34 12         ucomisd 0x12345678\(%rip\),%xmm1        # 123459f7 <_start\+0x123459f7>
-[      ]*[a-f0-9]+:    0f 2e 0d 78 56 34 12    ucomiss 0x12345678\(%rip\),%xmm1        # 123459fe <_start\+0x123459fe>
+[      ]*[a-f0-9]+:    f2 0f 7c 0d 78 56 34 12         haddps 0x12345678\(%rip\),%xmm1        # 12345966 <_start\+0x12345966>
+[      ]*[a-f0-9]+:    f3 0f 7f 0d 78 56 34 12         movdqu %xmm1,0x12345678\(%rip\)        # 1234596e <_start\+0x1234596e>
+[      ]*[a-f0-9]+:    f3 0f 6f 0d 78 56 34 12         movdqu 0x12345678\(%rip\),%xmm1        # 12345976 <_start\+0x12345976>
+[      ]*[a-f0-9]+:    66 0f 17 0d 78 56 34 12         movhpd %xmm1,0x12345678\(%rip\)        # 1234597e <_start\+0x1234597e>
+[      ]*[a-f0-9]+:    66 0f 16 0d 78 56 34 12         movhpd 0x12345678\(%rip\),%xmm1        # 12345986 <_start\+0x12345986>
+[      ]*[a-f0-9]+:    0f 17 0d 78 56 34 12    movhps %xmm1,0x12345678\(%rip\)        # 1234598d <_start\+0x1234598d>
+[      ]*[a-f0-9]+:    0f 16 0d 78 56 34 12    movhps 0x12345678\(%rip\),%xmm1        # 12345994 <_start\+0x12345994>
+[      ]*[a-f0-9]+:    66 0f 13 0d 78 56 34 12         movlpd %xmm1,0x12345678\(%rip\)        # 1234599c <_start\+0x1234599c>
+[      ]*[a-f0-9]+:    66 0f 12 0d 78 56 34 12         movlpd 0x12345678\(%rip\),%xmm1        # 123459a4 <_start\+0x123459a4>
+[      ]*[a-f0-9]+:    0f 13 0d 78 56 34 12    movlps %xmm1,0x12345678\(%rip\)        # 123459ab <_start\+0x123459ab>
+[      ]*[a-f0-9]+:    0f 12 0d 78 56 34 12    movlps 0x12345678\(%rip\),%xmm1        # 123459b2 <_start\+0x123459b2>
+[      ]*[a-f0-9]+:    66 0f d6 0d 78 56 34 12         movq   %xmm1,0x12345678\(%rip\)        # 123459ba <_start\+0x123459ba>
+[      ]*[a-f0-9]+:    f3 0f 7e 0d 78 56 34 12         movq   0x12345678\(%rip\),%xmm1        # 123459c2 <_start\+0x123459c2>
+[      ]*[a-f0-9]+:    f3 0f 16 0d 78 56 34 12         movshdup 0x12345678\(%rip\),%xmm1        # 123459ca <_start\+0x123459ca>
+[      ]*[a-f0-9]+:    f3 0f 12 0d 78 56 34 12         movsldup 0x12345678\(%rip\),%xmm1        # 123459d2 <_start\+0x123459d2>
+[      ]*[a-f0-9]+:    f3 0f 70 0d 78 56 34 12 90      pshufhw \$0x90,0x12345678\(%rip\),%xmm1        # 123459db <_start\+0x123459db>
+[      ]*[a-f0-9]+:    f2 0f 70 0d 78 56 34 12 90      pshuflw \$0x90,0x12345678\(%rip\),%xmm1        # 123459e4 <_start\+0x123459e4>
+[      ]*[a-f0-9]+:    0f 60 0d 78 56 34 12    punpcklbw 0x12345678\(%rip\),%mm1        # 123459eb <_start\+0x123459eb>
+[      ]*[a-f0-9]+:    0f 62 0d 78 56 34 12    punpckldq 0x12345678\(%rip\),%mm1        # 123459f2 <_start\+0x123459f2>
+[      ]*[a-f0-9]+:    0f 61 0d 78 56 34 12    punpcklwd 0x12345678\(%rip\),%mm1        # 123459f9 <_start\+0x123459f9>
+[      ]*[a-f0-9]+:    66 0f 60 0d 78 56 34 12         punpcklbw 0x12345678\(%rip\),%xmm1        # 12345a01 <_start\+0x12345a01>
+[      ]*[a-f0-9]+:    66 0f 62 0d 78 56 34 12         punpckldq 0x12345678\(%rip\),%xmm1        # 12345a09 <_start\+0x12345a09>
+[      ]*[a-f0-9]+:    66 0f 61 0d 78 56 34 12         punpcklwd 0x12345678\(%rip\),%xmm1        # 12345a11 <_start\+0x12345a11>
+[      ]*[a-f0-9]+:    66 0f 6c 0d 78 56 34 12         punpcklqdq 0x12345678\(%rip\),%xmm1        # 12345a19 <_start\+0x12345a19>
+[      ]*[a-f0-9]+:    66 0f 2e 0d 78 56 34 12         ucomisd 0x12345678\(%rip\),%xmm1        # 12345a21 <_start\+0x12345a21>
+[      ]*[a-f0-9]+:    0f 2e 0d 78 56 34 12    ucomiss 0x12345678\(%rip\),%xmm1        # 12345a28 <_start\+0x12345a28>
 [      ]*[a-f0-9]+:    f2 0f c2 00 00          cmpeqsd \(%rax\),%xmm0
 [      ]*[a-f0-9]+:    f3 0f c2 00 00          cmpeqss \(%rax\),%xmm0
 [      ]*[a-f0-9]+:    66 0f 2a 00             cvtpi2pd \(%rax\),%xmm0
@@ -220,4 +232,16 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f3 0f c2 38 10          cmpss  \$0x10,\(%rax\),%xmm7
 [      ]*[a-f0-9]+:    f2 0f c2 f7 10          cmpsd  \$0x10,%xmm7,%xmm6
 [      ]*[a-f0-9]+:    f2 0f c2 38 10          cmpsd  \$0x10,\(%rax\),%xmm7
+[      ]*[a-f0-9]+:    0f d4 08                paddq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    0f d4 08                paddq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    66 0f d4 08             paddq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    66 0f d4 08             paddq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    0f fb 08                psubq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    0f fb 08                psubq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    66 0f fb 08             psubq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    66 0f fb 08             psubq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    0f f4 08                pmuludq \(%rax\),%mm1
+[      ]*[a-f0-9]+:    0f f4 08                pmuludq \(%rax\),%mm1
+[      ]*[a-f0-9]+:    66 0f f4 08             pmuludq \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    66 0f f4 08             pmuludq \(%rax\),%xmm1
 #pass
index 3f0b98d..606448d 100644 (file)
@@ -112,13 +112,25 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f3 0f c2 38 10          cmpss  \$0x10,\(%rax\),%xmm7
 [      ]*[a-f0-9]+:    f2 0f c2 f7 10          cmpsd  \$0x10,%xmm7,%xmm6
 [      ]*[a-f0-9]+:    f2 0f c2 38 10          cmpsd  \$0x10,\(%rax\),%xmm7
-[      ]*[a-f0-9]+:    f2 0f d0 0d 78 56 34 12         addsubps 0x12345678\(%rip\),%xmm1        # 123458be <_start\+0x123458be>
-[      ]*[a-f0-9]+:    66 0f 2f 0d 78 56 34 12         comisd 0x12345678\(%rip\),%xmm1        # 123458c6 <_start\+0x123458c6>
-[      ]*[a-f0-9]+:    0f 2f 0d 78 56 34 12    comiss 0x12345678\(%rip\),%xmm1        # 123458cd <_start\+0x123458cd>
-[      ]*[a-f0-9]+:    f3 0f e6 0d 78 56 34 12         cvtdq2pd 0x12345678\(%rip\),%xmm1        # 123458d5 <_start\+0x123458d5>
-[      ]*[a-f0-9]+:    f2 0f e6 0d 78 56 34 12         cvtpd2dq 0x12345678\(%rip\),%xmm1        # 123458dd <_start\+0x123458dd>
-[      ]*[a-f0-9]+:    0f 5a 0d 78 56 34 12    cvtps2pd 0x12345678\(%rip\),%xmm1        # 123458e4 <_start\+0x123458e4>
-[      ]*[a-f0-9]+:    f3 0f 5b 0d 78 56 34 12         cvttps2dq 0x12345678\(%rip\),%xmm1        # 123458ec <_start\+0x123458ec>
+[      ]*[a-f0-9]+:    0f d4 c1                paddq  %mm1,%mm0
+[      ]*[a-f0-9]+:    0f d4 00                paddq  \(%rax\),%mm0
+[      ]*[a-f0-9]+:    66 0f d4 c1             paddq  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f d4 00             paddq  \(%rax\),%xmm0
+[      ]*[a-f0-9]+:    0f fb c1                psubq  %mm1,%mm0
+[      ]*[a-f0-9]+:    0f fb 00                psubq  \(%rax\),%mm0
+[      ]*[a-f0-9]+:    66 0f fb c1             psubq  %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f fb 00             psubq  \(%rax\),%xmm0
+[      ]*[a-f0-9]+:    0f f4 c1                pmuludq %mm1,%mm0
+[      ]*[a-f0-9]+:    0f f4 00                pmuludq \(%rax\),%mm0
+[      ]*[a-f0-9]+:    66 0f f4 c1             pmuludq %xmm1,%xmm0
+[      ]*[a-f0-9]+:    66 0f f4 00             pmuludq \(%rax\),%xmm0
+[      ]*[a-f0-9]+:    f2 0f d0 0d 78 56 34 12         addsubps 0x12345678\(%rip\),%xmm1        # 123458e8 <_start\+0x123458e8>
+[      ]*[a-f0-9]+:    66 0f 2f 0d 78 56 34 12         comisd 0x12345678\(%rip\),%xmm1        # 123458f0 <_start\+0x123458f0>
+[      ]*[a-f0-9]+:    0f 2f 0d 78 56 34 12    comiss 0x12345678\(%rip\),%xmm1        # 123458f7 <_start\+0x123458f7>
+[      ]*[a-f0-9]+:    f3 0f e6 0d 78 56 34 12         cvtdq2pd 0x12345678\(%rip\),%xmm1        # 123458ff <_start\+0x123458ff>
+[      ]*[a-f0-9]+:    f2 0f e6 0d 78 56 34 12         cvtpd2dq 0x12345678\(%rip\),%xmm1        # 12345907 <_start\+0x12345907>
+[      ]*[a-f0-9]+:    0f 5a 0d 78 56 34 12    cvtps2pd 0x12345678\(%rip\),%xmm1        # 1234590e <_start\+0x1234590e>
+[      ]*[a-f0-9]+:    f3 0f 5b 0d 78 56 34 12         cvttps2dq 0x12345678\(%rip\),%xmm1        # 12345916 <_start\+0x12345916>
 [      ]*[a-f0-9]+:    f3 0f 2a c8             cvtsi2ss %eax,%xmm1
 [      ]*[a-f0-9]+:    f2 0f 2a c8             cvtsi2sd %eax,%xmm1
 [      ]*[a-f0-9]+:    f3 0f 2a c8             cvtsi2ss %eax,%xmm1
@@ -135,32 +147,32 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f2 48 0f 2a 08          cvtsi2sdq \(%rax\),%xmm1
 [      ]*[a-f0-9]+:    f3 48 0f 2a 08          cvtsi2ssq \(%rax\),%xmm1
 [      ]*[a-f0-9]+:    f2 48 0f 2a 08          cvtsi2sdq \(%rax\),%xmm1
-[      ]*[a-f0-9]+:    f2 0f 7c 0d 78 56 34 12         haddps 0x12345678\(%rip\),%xmm1        # 1234593c <_start\+0x1234593c>
-[      ]*[a-f0-9]+:    f3 0f 7f 0d 78 56 34 12         movdqu %xmm1,0x12345678\(%rip\)        # 12345944 <_start\+0x12345944>
-[      ]*[a-f0-9]+:    f3 0f 6f 0d 78 56 34 12         movdqu 0x12345678\(%rip\),%xmm1        # 1234594c <_start\+0x1234594c>
-[      ]*[a-f0-9]+:    66 0f 17 0d 78 56 34 12         movhpd %xmm1,0x12345678\(%rip\)        # 12345954 <_start\+0x12345954>
-[      ]*[a-f0-9]+:    66 0f 16 0d 78 56 34 12         movhpd 0x12345678\(%rip\),%xmm1        # 1234595c <_start\+0x1234595c>
-[      ]*[a-f0-9]+:    0f 17 0d 78 56 34 12    movhps %xmm1,0x12345678\(%rip\)        # 12345963 <_start\+0x12345963>
-[      ]*[a-f0-9]+:    0f 16 0d 78 56 34 12    movhps 0x12345678\(%rip\),%xmm1        # 1234596a <_start\+0x1234596a>
-[      ]*[a-f0-9]+:    66 0f 13 0d 78 56 34 12         movlpd %xmm1,0x12345678\(%rip\)        # 12345972 <_start\+0x12345972>
-[      ]*[a-f0-9]+:    66 0f 12 0d 78 56 34 12         movlpd 0x12345678\(%rip\),%xmm1        # 1234597a <_start\+0x1234597a>
-[      ]*[a-f0-9]+:    0f 13 0d 78 56 34 12    movlps %xmm1,0x12345678\(%rip\)        # 12345981 <_start\+0x12345981>
-[      ]*[a-f0-9]+:    0f 12 0d 78 56 34 12    movlps 0x12345678\(%rip\),%xmm1        # 12345988 <_start\+0x12345988>
-[      ]*[a-f0-9]+:    66 0f d6 0d 78 56 34 12         movq   %xmm1,0x12345678\(%rip\)        # 12345990 <_start\+0x12345990>
-[      ]*[a-f0-9]+:    f3 0f 7e 0d 78 56 34 12         movq   0x12345678\(%rip\),%xmm1        # 12345998 <_start\+0x12345998>
-[      ]*[a-f0-9]+:    f3 0f 16 0d 78 56 34 12         movshdup 0x12345678\(%rip\),%xmm1        # 123459a0 <_start\+0x123459a0>
-[      ]*[a-f0-9]+:    f3 0f 12 0d 78 56 34 12         movsldup 0x12345678\(%rip\),%xmm1        # 123459a8 <_start\+0x123459a8>
-[      ]*[a-f0-9]+:    f3 0f 70 0d 78 56 34 12 90      pshufhw \$0x90,0x12345678\(%rip\),%xmm1        # 123459b1 <_start\+0x123459b1>
-[      ]*[a-f0-9]+:    f2 0f 70 0d 78 56 34 12 90      pshuflw \$0x90,0x12345678\(%rip\),%xmm1        # 123459ba <_start\+0x123459ba>
-[      ]*[a-f0-9]+:    0f 60 0d 78 56 34 12    punpcklbw 0x12345678\(%rip\),%mm1        # 123459c1 <_start\+0x123459c1>
-[      ]*[a-f0-9]+:    0f 62 0d 78 56 34 12    punpckldq 0x12345678\(%rip\),%mm1        # 123459c8 <_start\+0x123459c8>
-[      ]*[a-f0-9]+:    0f 61 0d 78 56 34 12    punpcklwd 0x12345678\(%rip\),%mm1        # 123459cf <_start\+0x123459cf>
-[      ]*[a-f0-9]+:    66 0f 60 0d 78 56 34 12         punpcklbw 0x12345678\(%rip\),%xmm1        # 123459d7 <_start\+0x123459d7>
-[      ]*[a-f0-9]+:    66 0f 62 0d 78 56 34 12         punpckldq 0x12345678\(%rip\),%xmm1        # 123459df <_start\+0x123459df>
-[      ]*[a-f0-9]+:    66 0f 61 0d 78 56 34 12         punpcklwd 0x12345678\(%rip\),%xmm1        # 123459e7 <_start\+0x123459e7>
-[      ]*[a-f0-9]+:    66 0f 6c 0d 78 56 34 12         punpcklqdq 0x12345678\(%rip\),%xmm1        # 123459ef <_start\+0x123459ef>
-[      ]*[a-f0-9]+:    66 0f 2e 0d 78 56 34 12         ucomisd 0x12345678\(%rip\),%xmm1        # 123459f7 <_start\+0x123459f7>
-[      ]*[a-f0-9]+:    0f 2e 0d 78 56 34 12    ucomiss 0x12345678\(%rip\),%xmm1        # 123459fe <_start\+0x123459fe>
+[      ]*[a-f0-9]+:    f2 0f 7c 0d 78 56 34 12         haddps 0x12345678\(%rip\),%xmm1        # 12345966 <_start\+0x12345966>
+[      ]*[a-f0-9]+:    f3 0f 7f 0d 78 56 34 12         movdqu %xmm1,0x12345678\(%rip\)        # 1234596e <_start\+0x1234596e>
+[      ]*[a-f0-9]+:    f3 0f 6f 0d 78 56 34 12         movdqu 0x12345678\(%rip\),%xmm1        # 12345976 <_start\+0x12345976>
+[      ]*[a-f0-9]+:    66 0f 17 0d 78 56 34 12         movhpd %xmm1,0x12345678\(%rip\)        # 1234597e <_start\+0x1234597e>
+[      ]*[a-f0-9]+:    66 0f 16 0d 78 56 34 12         movhpd 0x12345678\(%rip\),%xmm1        # 12345986 <_start\+0x12345986>
+[      ]*[a-f0-9]+:    0f 17 0d 78 56 34 12    movhps %xmm1,0x12345678\(%rip\)        # 1234598d <_start\+0x1234598d>
+[      ]*[a-f0-9]+:    0f 16 0d 78 56 34 12    movhps 0x12345678\(%rip\),%xmm1        # 12345994 <_start\+0x12345994>
+[      ]*[a-f0-9]+:    66 0f 13 0d 78 56 34 12         movlpd %xmm1,0x12345678\(%rip\)        # 1234599c <_start\+0x1234599c>
+[      ]*[a-f0-9]+:    66 0f 12 0d 78 56 34 12         movlpd 0x12345678\(%rip\),%xmm1        # 123459a4 <_start\+0x123459a4>
+[      ]*[a-f0-9]+:    0f 13 0d 78 56 34 12    movlps %xmm1,0x12345678\(%rip\)        # 123459ab <_start\+0x123459ab>
+[      ]*[a-f0-9]+:    0f 12 0d 78 56 34 12    movlps 0x12345678\(%rip\),%xmm1        # 123459b2 <_start\+0x123459b2>
+[      ]*[a-f0-9]+:    66 0f d6 0d 78 56 34 12         movq   %xmm1,0x12345678\(%rip\)        # 123459ba <_start\+0x123459ba>
+[      ]*[a-f0-9]+:    f3 0f 7e 0d 78 56 34 12         movq   0x12345678\(%rip\),%xmm1        # 123459c2 <_start\+0x123459c2>
+[      ]*[a-f0-9]+:    f3 0f 16 0d 78 56 34 12         movshdup 0x12345678\(%rip\),%xmm1        # 123459ca <_start\+0x123459ca>
+[      ]*[a-f0-9]+:    f3 0f 12 0d 78 56 34 12         movsldup 0x12345678\(%rip\),%xmm1        # 123459d2 <_start\+0x123459d2>
+[      ]*[a-f0-9]+:    f3 0f 70 0d 78 56 34 12 90      pshufhw \$0x90,0x12345678\(%rip\),%xmm1        # 123459db <_start\+0x123459db>
+[      ]*[a-f0-9]+:    f2 0f 70 0d 78 56 34 12 90      pshuflw \$0x90,0x12345678\(%rip\),%xmm1        # 123459e4 <_start\+0x123459e4>
+[      ]*[a-f0-9]+:    0f 60 0d 78 56 34 12    punpcklbw 0x12345678\(%rip\),%mm1        # 123459eb <_start\+0x123459eb>
+[      ]*[a-f0-9]+:    0f 62 0d 78 56 34 12    punpckldq 0x12345678\(%rip\),%mm1        # 123459f2 <_start\+0x123459f2>
+[      ]*[a-f0-9]+:    0f 61 0d 78 56 34 12    punpcklwd 0x12345678\(%rip\),%mm1        # 123459f9 <_start\+0x123459f9>
+[      ]*[a-f0-9]+:    66 0f 60 0d 78 56 34 12         punpcklbw 0x12345678\(%rip\),%xmm1        # 12345a01 <_start\+0x12345a01>
+[      ]*[a-f0-9]+:    66 0f 62 0d 78 56 34 12         punpckldq 0x12345678\(%rip\),%xmm1        # 12345a09 <_start\+0x12345a09>
+[      ]*[a-f0-9]+:    66 0f 61 0d 78 56 34 12         punpcklwd 0x12345678\(%rip\),%xmm1        # 12345a11 <_start\+0x12345a11>
+[      ]*[a-f0-9]+:    66 0f 6c 0d 78 56 34 12         punpcklqdq 0x12345678\(%rip\),%xmm1        # 12345a19 <_start\+0x12345a19>
+[      ]*[a-f0-9]+:    66 0f 2e 0d 78 56 34 12         ucomisd 0x12345678\(%rip\),%xmm1        # 12345a21 <_start\+0x12345a21>
+[      ]*[a-f0-9]+:    0f 2e 0d 78 56 34 12    ucomiss 0x12345678\(%rip\),%xmm1        # 12345a28 <_start\+0x12345a28>
 [      ]*[a-f0-9]+:    f2 0f c2 00 00          cmpeqsd \(%rax\),%xmm0
 [      ]*[a-f0-9]+:    f3 0f c2 00 00          cmpeqss \(%rax\),%xmm0
 [      ]*[a-f0-9]+:    66 0f 2a 00             cvtpi2pd \(%rax\),%xmm0
@@ -219,4 +231,16 @@ Disassembly of section .text:
 [      ]*[a-f0-9]+:    f3 0f c2 38 10          cmpss  \$0x10,\(%rax\),%xmm7
 [      ]*[a-f0-9]+:    f2 0f c2 f7 10          cmpsd  \$0x10,%xmm7,%xmm6
 [      ]*[a-f0-9]+:    f2 0f c2 38 10          cmpsd  \$0x10,\(%rax\),%xmm7
+[      ]*[a-f0-9]+:    0f d4 08                paddq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    0f d4 08                paddq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    66 0f d4 08             paddq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    66 0f d4 08             paddq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    0f fb 08                psubq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    0f fb 08                psubq  \(%rax\),%mm1
+[      ]*[a-f0-9]+:    66 0f fb 08             psubq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    66 0f fb 08             psubq  \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    0f f4 08                pmuludq \(%rax\),%mm1
+[      ]*[a-f0-9]+:    0f f4 08                pmuludq \(%rax\),%mm1
+[      ]*[a-f0-9]+:    66 0f f4 08             pmuludq \(%rax\),%xmm1
+[      ]*[a-f0-9]+:    66 0f f4 08             pmuludq \(%rax\),%xmm1
 #pass
index 5c1d8d1..2b44a4e 100644 (file)
@@ -110,6 +110,21 @@ cmpss      $0x10,(%rax),%xmm7
 cmpsd  $0x10,%xmm7,%xmm6
 cmpsd  $0x10,(%rax),%xmm7
 
+       paddq %mm1,%mm0
+       paddq (%rax),%mm0
+       paddq %xmm1,%xmm0
+       paddq (%rax),%xmm0
+
+       psubq %mm1,%mm0
+       psubq (%rax),%mm0
+       psubq %xmm1,%xmm0
+       psubq (%rax),%xmm0
+
+       pmuludq %mm1,%mm0
+       pmuludq (%rax),%mm0
+       pmuludq %xmm1,%xmm0
+       pmuludq (%rax),%xmm0
+
        .intel_syntax noprefix
 
 addsubps xmm1,XMMWORD PTR [rip+0x12345678]        
@@ -219,3 +234,15 @@ cmpss  xmm6,xmm7,0x10
 cmpss  xmm7,DWORD PTR [rax],0x10
 cmpsd  xmm6,xmm7,0x10
 cmpsd  xmm7,QWORD PTR [rax],0x10
+paddq mm1,QWORD PTR [rax]
+paddq mm1,QWORD PTR [rax]
+paddq xmm1,XMMWORD PTR [rax]
+paddq xmm1,XMMWORD PTR [rax]
+psubq mm1,QWORD PTR [rax]
+psubq mm1,QWORD PTR [rax]
+psubq xmm1,XMMWORD PTR [rax]
+psubq xmm1,XMMWORD PTR [rax]
+pmuludq mm1,QWORD PTR [rax]
+pmuludq mm1,QWORD PTR [rax]
+pmuludq xmm1,XMMWORD PTR [rax]
+pmuludq xmm1,XMMWORD PTR [rax]