Add support for VSX scalar single-precision arithmetic in the PPC target

http://reviews.llvm.org/D9891
Following up on the VSX single precision loads and stores added earlier, this
adds support for elementary arithmetic operations on single precision values
in VSX registers. These instructions utilize the new VSSRC register class.
Instructions added:
xsaddsp
xsdivsp
xsmulsp
xsresp
xsrsqrtesp
xssqrtsp
xssubsp

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237937 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/PowerPC/PPCInstrVSX.td b/lib/Target/PowerPC/PPCInstrVSX.td
index d93fd5e27d68caf9977f177bddfd7d9f0e1e677a..9685bac2aebbb86b4ebf2424317c2ecfaeef2d38 100644 (file)
--- a/lib/Target/PowerPC/PPCInstrVSX.td
+++ b/lib/Target/PowerPC/PPCInstrVSX.td
@@ -989,21 +989,23 @@ def HasP8Vector : Predicate<"PPCSubTarget->hasP8Vector()">;
 def HasDirectMove : Predicate<"PPCSubTarget->hasDirectMove()">;
 let Predicates = [HasP8Vector] in {
 let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
-let isCommutable = 1 in {
-  def XXLEQV : XX3Form<60, 186,
-                       (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
-                       "xxleqv $XT, $XA, $XB", IIC_VecGeneral,
-                       [(set v4i32:$XT, (vnot_ppc (xor v4i32:$XA, v4i32:$XB)))]>;
-  def XXLNAND : XX3Form<60, 178,
-                        (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
-                        "xxlnand $XT, $XA, $XB", IIC_VecGeneral,
-                        [(set v4i32:$XT, (vnot_ppc (and v4i32:$XA,
+  let isCommutable = 1 in {
+    def XXLEQV : XX3Form<60, 186,
+                         (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
+                         "xxleqv $XT, $XA, $XB", IIC_VecGeneral,
+                         [(set v4i32:$XT, (vnot_ppc (xor v4i32:$XA, v4i32:$XB)))]>;
+    def XXLNAND : XX3Form<60, 178,
+                          (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
+                          "xxlnand $XT, $XA, $XB", IIC_VecGeneral,
+                          [(set v4i32:$XT, (vnot_ppc (and v4i32:$XA,
                                                     v4i32:$XB)))]>;
   } // isCommutable
-def XXLORC : XX3Form<60, 170,
-                     (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
-                     "xxlorc $XT, $XA, $XB", IIC_VecGeneral,
-                     [(set v4i32:$XT, (or v4i32:$XA, (vnot_ppc v4i32:$XB)))]>;
+
+  def XXLORC : XX3Form<60, 170,
+                       (outs vsrc:$XT), (ins vsrc:$XA, vsrc:$XB),
+                       "xxlorc $XT, $XA, $XB", IIC_VecGeneral,
+                       [(set v4i32:$XT, (or v4i32:$XA, (vnot_ppc v4i32:$XB)))]>;
+
   // VSX scalar loads introduced in ISA 2.07
   let mayLoad = 1 in {
     def LXSSPX : XX1Form<31, 524, (outs vssrc:$XT), (ins memrr:$src),
@@ -1026,42 +1028,76 @@ def XXLORC : XX3Form<60, 170,
                           "stxsiwx $XT, $dst", IIC_LdStSTFD,
                           [(PPCstfiwx f64:$XT, xoaddr:$dst)]>;
   } // mayStore
-def : Pat<(f64 (extloadf32 xoaddr:$src)),
-          (COPY_TO_REGCLASS (LXSSPX xoaddr:$src), VSFRC)>;
-def : Pat<(f64 (fextend f32:$src)),
-          (COPY_TO_REGCLASS $src, VSFRC)>;
-def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLT)),
-          (SELECT_VSSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
-def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLE)),
-          (SELECT_VSSRC (CRORC  $rhs, $lhs), $tval, $fval)>;
-def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETEQ)),
-          (SELECT_VSSRC (CREQV $lhs, $rhs), $tval, $fval)>;
-def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGE)),
-          (SELECT_VSSRC (CRORC  $lhs, $rhs), $tval, $fval)>;
-def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGT)),
-          (SELECT_VSSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
-def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETNE)),
+
+  def : Pat<(f64 (extloadf32 xoaddr:$src)),
+            (COPY_TO_REGCLASS (LXSSPX xoaddr:$src), VSFRC)>;
+  def : Pat<(f64 (fextend f32:$src)),
+            (COPY_TO_REGCLASS $src, VSFRC)>;
+  def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLT)),
+            (SELECT_VSSRC (CRANDC $rhs, $lhs), $tval, $fval)>;
+  def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETLE)),
+            (SELECT_VSSRC (CRORC  $rhs, $lhs), $tval, $fval)>;
+  def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETEQ)),
+            (SELECT_VSSRC (CREQV $lhs, $rhs), $tval, $fval)>;
+  def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGE)),
+            (SELECT_VSSRC (CRORC  $lhs, $rhs), $tval, $fval)>;
+  def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETGT)),
+            (SELECT_VSSRC (CRANDC $lhs, $rhs), $tval, $fval)>;
+  def : Pat<(f32 (selectcc i1:$lhs, i1:$rhs, f32:$tval, f32:$fval, SETNE)),
           (SELECT_VSSRC (CRXOR $lhs, $rhs), $tval, $fval)>;
+
+  // VSX Elementary Scalar FP arithmetic (SP)
+  let isCommutable = 1 in {
+    def XSADDSP : XX3Form<60, 0,
+                          (outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
+                          "xsaddsp $XT, $XA, $XB", IIC_VecFP,
+                          [(set f32:$XT, (fadd f32:$XA, f32:$XB))]>;
+    def XSMULSP : XX3Form<60, 16,
+                          (outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
+                          "xsmulsp $XT, $XA, $XB", IIC_VecFP,
+                          [(set f32:$XT, (fmul f32:$XA, f32:$XB))]>;
+  } // isCommutable
+
+  def XSDIVSP : XX3Form<60, 24,
+                        (outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
+                        "xsdivsp $XT, $XA, $XB", IIC_FPDivS,
+                        [(set f32:$XT, (fdiv f32:$XA, f32:$XB))]>;
+  def XSRESP : XX2Form<60, 26,
+                        (outs vssrc:$XT), (ins vssrc:$XB),
+                        "xsresp $XT, $XB", IIC_VecFP,
+                        [(set f32:$XT, (PPCfre f32:$XB))]>;
+  def XSSQRTSP : XX2Form<60, 11,
+                        (outs vssrc:$XT), (ins vssrc:$XB),
+                        "xssqrtsp $XT, $XB", IIC_FPSqrtS,
+                        [(set f32:$XT, (fsqrt f32:$XB))]>;
+  def XSRSQRTESP : XX2Form<60, 10,
+                           (outs vssrc:$XT), (ins vssrc:$XB),
+                           "xsrsqrtesp $XT, $XB", IIC_VecFP,
+                           [(set f32:$XT, (PPCfrsqrte f32:$XB))]>;
+  def XSSUBSP : XX3Form<60, 8,
+                        (outs vssrc:$XT), (ins vssrc:$XA, vssrc:$XB),
+                        "xssubsp $XT, $XA, $XB", IIC_VecFP,
+                        [(set f32:$XT, (fsub f32:$XA, f32:$XB))]>;
 } // AddedComplexity = 400
 } // HasP8Vector
 
 let Predicates = [HasDirectMove, HasVSX] in {
-// VSX direct move instructions
-def MFVSRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vsfrc:$XT),
-                            "mfvsrd $rA, $XT", IIC_VecGeneral,
-                            [(set i64:$rA, (PPCmfvsr f64:$XT))]>,
-    Requires<[In64BitMode]>;
-def MFVSRWZ : XX1_RS6_RD5_XO<31, 115, (outs gprc:$rA), (ins vsfrc:$XT),
-                             "mfvsrwz $rA, $XT", IIC_VecGeneral,
-                             [(set i32:$rA, (PPCmfvsr f64:$XT))]>;
-def MTVSRD : XX1_RS6_RD5_XO<31, 179, (outs vsfrc:$XT), (ins g8rc:$rA),
-                            "mtvsrd $XT, $rA", IIC_VecGeneral,
-                            [(set f64:$XT, (PPCmtvsra i64:$rA))]>,
-    Requires<[In64BitMode]>;
-def MTVSRWA : XX1_RS6_RD5_XO<31, 211, (outs vsfrc:$XT), (ins gprc:$rA),
-                             "mtvsrwa $XT, $rA", IIC_VecGeneral,
-                             [(set f64:$XT, (PPCmtvsra i32:$rA))]>;
-def MTVSRWZ : XX1_RS6_RD5_XO<31, 243, (outs vsfrc:$XT), (ins gprc:$rA),
-                             "mtvsrwz $XT, $rA", IIC_VecGeneral,
-                             [(set f64:$XT, (PPCmtvsrz i32:$rA))]>;
+  // VSX direct move instructions
+  def MFVSRD : XX1_RS6_RD5_XO<31, 51, (outs g8rc:$rA), (ins vsfrc:$XT),
+                              "mfvsrd $rA, $XT", IIC_VecGeneral,
+                              [(set i64:$rA, (PPCmfvsr f64:$XT))]>,
+      Requires<[In64BitMode]>;
+  def MFVSRWZ : XX1_RS6_RD5_XO<31, 115, (outs gprc:$rA), (ins vsfrc:$XT),
+                               "mfvsrwz $rA, $XT", IIC_VecGeneral,
+                               [(set i32:$rA, (PPCmfvsr f64:$XT))]>;
+  def MTVSRD : XX1_RS6_RD5_XO<31, 179, (outs vsfrc:$XT), (ins g8rc:$rA),
+                              "mtvsrd $XT, $rA", IIC_VecGeneral,
+                              [(set f64:$XT, (PPCmtvsra i64:$rA))]>,
+      Requires<[In64BitMode]>;
+  def MTVSRWA : XX1_RS6_RD5_XO<31, 211, (outs vsfrc:$XT), (ins gprc:$rA),
+                               "mtvsrwa $XT, $rA", IIC_VecGeneral,
+                               [(set f64:$XT, (PPCmtvsra i32:$rA))]>;
+  def MTVSRWZ : XX1_RS6_RD5_XO<31, 243, (outs vsfrc:$XT), (ins gprc:$rA),
+                               "mtvsrwz $XT, $rA", IIC_VecGeneral,
+                               [(set f64:$XT, (PPCmtvsrz i32:$rA))]>;
 } // HasDirectMove, HasVSX

diff --git a/test/CodeGen/PowerPC/vsx-elementary-arith.ll b/test/CodeGen/PowerPC/vsx-elementary-arith.ll
new file mode 100644 (file)
index 0000000..d8f76bb
--- /dev/null
+++ b/test/CodeGen/PowerPC/vsx-elementary-arith.ll
@@ -0,0 +1,120 @@
+; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 | FileCheck %s
+; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 | FileCheck %s
+@a = global float 3.000000e+00, align 4
+@b = global float 4.000000e+00, align 4
+@c = global double 3.000000e+00, align 8
+@d = global double 4.000000e+00, align 8
+
+; Function Attrs: nounwind
+define float @emit_xsaddsp() {
+entry:
+  %0 = load float, float* @a, align 4
+  %1 = load float, float* @b, align 4
+  %add = fadd float %0, %1
+  ret float %add
+; CHECK-LABEL: @emit_xsaddsp
+; CHECK: xsaddsp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define float @emit_xssubsp() {
+entry:
+  %0 = load float, float* @a, align 4
+  %1 = load float, float* @b, align 4
+  %sub = fsub float %0, %1
+  ret float %sub
+; CHECK-LABEL: @emit_xssubsp
+; CHECK: xssubsp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define float @emit_xsdivsp() {
+entry:
+  %0 = load float, float* @a, align 4
+  %1 = load float, float* @b, align 4
+  %div = fdiv float %0, %1
+  ret float %div
+; CHECK-LABEL: @emit_xsdivsp
+; CHECK: xsdivsp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define float @emit_xsmulsp() {
+entry:
+  %0 = load float, float* @a, align 4
+  %1 = load float, float* @b, align 4
+  %mul = fmul float %0, %1
+  ret float %mul
+; CHECK-LABEL: @emit_xsmulsp
+; CHECK: xsmulsp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define float @emit_xssqrtsp() {
+entry:
+  %0 = load float, float* @b, align 4
+  %call = call float @sqrtf(float %0)
+  ret float %call
+; CHECK-LABEL: @emit_xssqrtsp
+; CHECK: xssqrtsp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+declare float @sqrtf(float)
+
+; Function Attrs: nounwind
+define double @emit_xsadddp() {
+entry:
+  %0 = load double, double* @c, align 8
+  %1 = load double, double* @d, align 8
+  %add = fadd double %0, %1
+  ret double %add
+; CHECK-LABEL: @emit_xsadddp
+; CHECK: xsadddp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define double @emit_xssubdp() {
+entry:
+  %0 = load double, double* @c, align 8
+  %1 = load double, double* @d, align 8
+  %sub = fsub double %0, %1
+  ret double %sub
+; CHECK-LABEL: @emit_xssubdp
+; CHECK: xssubdp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define double @emit_xsdivdp() {
+entry:
+  %0 = load double, double* @c, align 8
+  %1 = load double, double* @d, align 8
+  %div = fdiv double %0, %1
+  ret double %div
+; CHECK-LABEL: @emit_xsdivdp
+; CHECK: xsdivdp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define double @emit_xsmuldp() {
+entry:
+  %0 = load double, double* @c, align 8
+  %1 = load double, double* @d, align 8
+  %mul = fmul double %0, %1
+  ret double %mul
+; CHECK-LABEL: @emit_xsmuldp
+; CHECK: xsmuldp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define double @emit_xssqrtdp() {
+entry:
+  %0 = load double, double* @d, align 8
+  %call = call double @sqrt(double %0)
+  ret double %call
+; CHECK-LABEL: @emit_xssqrtdp
+; CHECK: xssqrtdp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+declare double @sqrt(double)

diff --git a/test/CodeGen/PowerPC/vsx-recip-est.ll b/test/CodeGen/PowerPC/vsx-recip-est.ll
new file mode 100644 (file)
index 0000000..f589c6c
--- /dev/null
+++ b/test/CodeGen/PowerPC/vsx-recip-est.ll
@@ -0,0 +1,62 @@
+; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 -enable-unsafe-fp-math | FileCheck %s
+; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 -enable-unsafe-fp-math | FileCheck %s
+@a = global float 3.000000e+00, align 4
+@b = global float 4.000000e+00, align 4
+@c = global double 3.000000e+00, align 8
+@d = global double 4.000000e+00, align 8
+
+; Function Attrs: nounwind
+define float @emit_xsresp() {
+entry:
+  %0 = load float, float* @a, align 4
+  %1 = load float, float* @b, align 4
+  %div = fdiv fast float %0, %1
+  ret float %div
+; CHECK-LABEL: @emit_xsresp
+; CHECK: xsresp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define float @emit_xsrsqrtesp(float %f) {
+entry:
+  %f.addr = alloca float, align 4
+  store float %f, float* %f.addr, align 4
+  %0 = load float, float* %f.addr, align 4
+  %1 = load float, float* @b, align 4
+  %2 = call float @llvm.sqrt.f32(float %1)
+  %div = fdiv fast float %0, %2
+  ret float %div
+; CHECK-LABEL: @emit_xsrsqrtesp
+; CHECK: xsrsqrtesp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind readnone
+declare float @llvm.sqrt.f32(float)
+
+; Function Attrs: nounwind
+define double @emit_xsredp() {
+entry:
+  %0 = load double, double* @c, align 8
+  %1 = load double, double* @d, align 8
+  %div = fdiv fast double %0, %1
+  ret double %div
+; CHECK-LABEL: @emit_xsredp
+; CHECK: xsredp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind
+define double @emit_xsrsqrtedp(double %f) {
+entry:
+  %f.addr = alloca double, align 8
+  store double %f, double* %f.addr, align 8
+  %0 = load double, double* %f.addr, align 8
+  %1 = load double, double* @d, align 8
+  %2 = call double @llvm.sqrt.f64(double %1)
+  %div = fdiv fast double %0, %2
+  ret double %div
+; CHECK-LABEL: @emit_xsrsqrtedp
+; CHECK: xsrsqrtedp {{[0-9]+}}
+}
+
+; Function Attrs: nounwind readnone
+declare double @llvm.sqrt.f64(double) #1

diff --git a/test/MC/Disassembler/PowerPC/vsx.txt b/test/MC/Disassembler/PowerPC/vsx.txt
index 417efd0fe17130af8720ca497a30f9648edf5e25..04b2eeb0dd2aa3d0bd8a142d5dd3fdb30e08137f 100644 (file)
--- a/test/MC/Disassembler/PowerPC/vsx.txt
+++ b/test/MC/Disassembler/PowerPC/vsx.txt
@@ -39,6 +39,9 @@
 # CHECK: xsabsdp 7, 27
 0xf0 0xe0 0xdd 0x64
 
+# CHECK: xsaddsp 7, 63, 27
+0xf0 0xff 0xd8 0x04
+
 # CHECK: xsadddp 7, 63, 27
 0xf0 0xff 0xd9 0x04
 
@@ -75,6 +78,9 @@
 # CHECK: xscvuxddp 7, 27
 0xf0 0xe0 0xdd 0xa0
 
+# CHECK: xsdivsp 7, 63, 27
+0xf0 0xff 0xd8 0xc4
+
 # CHECK: xsdivdp 7, 63, 27
 0xf0 0xff 0xd9 0xc4
 
@@ -96,6 +102,9 @@
 # CHECK: xsmsubmdp 7, 63, 27
 0xf0 0xff 0xd9 0xcc
 
+# CHECK: xsmulsp 7, 63, 27
+0xf0 0xff 0xd8 0x84
+
 # CHECK: xsmuldp 7, 63, 27
 0xf0 0xff 0xd9 0x84
 
@@ -132,15 +141,27 @@
 # CHECK: xsrdpiz 7, 27
 0xf0 0xe0 0xd9 0x64
 
+# CHECK: xsresp 7, 27
+0xf0 0xe0 0xd8 0x68
+
 # CHECK: xsredp 7, 27
 0xf0 0xe0 0xd9 0x68
 
+# CHECK: xsrsqrtesp 7, 27
+0xf0 0xe0 0xd8 0x28
+
 # CHECK: xsrsqrtedp 7, 27
 0xf0 0xe0 0xd9 0x28
 
+# CHECK: xssqrtsp 7, 27
+0xf0 0xe0 0xd8 0x2c
+
 # CHECK: xssqrtdp 7, 27
 0xf0 0xe0 0xd9 0x2c
 
+# CHECK: xssubsp 7, 63, 27
+0xf0 0xff 0xd8 0x44
+
 # CHECK: xssubdp 7, 63, 27
 0xf0 0xff 0xd9 0x44
 

diff --git a/test/MC/PowerPC/vsx.s b/test/MC/PowerPC/vsx.s
index 75c934f78c1380a99e97a3ca0b1a315b9350ab1a..773fc9eef6d16b6aa4c644d46507daf555ba2b3b 100644 (file)
--- a/test/MC/PowerPC/vsx.s
+++ b/test/MC/PowerPC/vsx.s
@@ -44,6 +44,9 @@
 # CHECK-BE: xsabsdp 7, 27                      # encoding: [0xf0,0xe0,0xdd,0x64]
 # CHECK-LE: xsabsdp 7, 27                      # encoding: [0x64,0xdd,0xe0,0xf0]
             xsabsdp 7, 27
+# CHECK-BE: xsaddsp 7, 63, 27                  # encoding: [0xf0,0xff,0xd8,0x04]
+# CHECK-LE: xsaddsp 7, 63, 27                  # encoding: [0x04,0xd8,0xff,0xf0]
+            xsaddsp 7, 63, 27
 # CHECK-BE: xsadddp 7, 63, 27                  # encoding: [0xf0,0xff,0xd9,0x04]
 # CHECK-LE: xsadddp 7, 63, 27                  # encoding: [0x04,0xd9,0xff,0xf0]
             xsadddp 7, 63, 27
@@ -80,6 +83,9 @@
 # CHECK-BE: xscvuxddp 7, 27                    # encoding: [0xf0,0xe0,0xdd,0xa0]
 # CHECK-LE: xscvuxddp 7, 27                    # encoding: [0xa0,0xdd,0xe0,0xf0]
             xscvuxddp 7, 27
+# CHECK-BE: xsdivsp 7, 63, 27                  # encoding: [0xf0,0xff,0xd8,0xc4]
+# CHECK-LE: xsdivsp 7, 63, 27                  # encoding: [0xc4,0xd8,0xff,0xf0]
+            xsdivsp 7, 63, 27
 # CHECK-BE: xsdivdp 7, 63, 27                  # encoding: [0xf0,0xff,0xd9,0xc4]
 # CHECK-LE: xsdivdp 7, 63, 27                  # encoding: [0xc4,0xd9,0xff,0xf0]
             xsdivdp 7, 63, 27
@@ -101,6 +107,9 @@
 # CHECK-BE: xsmsubmdp 7, 63, 27                # encoding: [0xf0,0xff,0xd9,0xcc]
 # CHECK-LE: xsmsubmdp 7, 63, 27                # encoding: [0xcc,0xd9,0xff,0xf0]
             xsmsubmdp 7, 63, 27
+# CHECK-BE: xsmulsp 7, 63, 27                  # encoding: [0xf0,0xff,0xd8,0x84]
+# CHECK-LE: xsmulsp 7, 63, 27                  # encoding: [0x84,0xd8,0xff,0xf0]
+            xsmulsp 7, 63, 27
 # CHECK-BE: xsmuldp 7, 63, 27                  # encoding: [0xf0,0xff,0xd9,0x84]
 # CHECK-LE: xsmuldp 7, 63, 27                  # encoding: [0x84,0xd9,0xff,0xf0]
             xsmuldp 7, 63, 27
@@ -137,15 +146,27 @@
 # CHECK-BE: xsrdpiz 7, 27                      # encoding: [0xf0,0xe0,0xd9,0x64]
 # CHECK-LE: xsrdpiz 7, 27                      # encoding: [0x64,0xd9,0xe0,0xf0]
             xsrdpiz 7, 27
+# CHECK-BE: xsresp 7, 27                       # encoding: [0xf0,0xe0,0xd8,0x68]
+# CHECK-LE: xsresp 7, 27                       # encoding: [0x68,0xd8,0xe0,0xf0]
+            xsresp 7, 27
 # CHECK-BE: xsredp 7, 27                       # encoding: [0xf0,0xe0,0xd9,0x68]
 # CHECK-LE: xsredp 7, 27                       # encoding: [0x68,0xd9,0xe0,0xf0]
             xsredp 7, 27
+# CHECK-BE: xsrsqrtesp 7, 27                   # encoding: [0xf0,0xe0,0xd8,0x28]
+# CHECK-LE: xsrsqrtesp 7, 27                   # encoding: [0x28,0xd8,0xe0,0xf0]
+            xsrsqrtesp 7, 27
 # CHECK-BE: xsrsqrtedp 7, 27                   # encoding: [0xf0,0xe0,0xd9,0x28]
 # CHECK-LE: xsrsqrtedp 7, 27                   # encoding: [0x28,0xd9,0xe0,0xf0]
             xsrsqrtedp 7, 27
+# CHECK-BE: xssqrtsp 7, 27                     # encoding: [0xf0,0xe0,0xd8,0x2c]
+# CHECK-LE: xssqrtsp 7, 27                     # encoding: [0x2c,0xd8,0xe0,0xf0]
+            xssqrtsp 7, 27
 # CHECK-BE: xssqrtdp 7, 27                     # encoding: [0xf0,0xe0,0xd9,0x2c]
 # CHECK-LE: xssqrtdp 7, 27                     # encoding: [0x2c,0xd9,0xe0,0xf0]
             xssqrtdp 7, 27
+# CHECK-BE: xssubsp 7, 63, 27                  # encoding: [0xf0,0xff,0xd8,0x44]
+# CHECK-LE: xssubsp 7, 63, 27                  # encoding: [0x44,0xd8,0xff,0xf0]
+            xssubsp 7, 63, 27
 # CHECK-BE: xssubdp 7, 63, 27                  # encoding: [0xf0,0xff,0xd9,0x44]
 # CHECK-LE: xssubdp 7, 63, 27                  # encoding: [0x44,0xd9,0xff,0xf0]
             xssubdp 7, 63, 27