target-ppc: Add VSX Vector Compare Instructions

This patch adds the VSX floating point compare vector instructions:

  - xvcmpeqdp[.], xvcmpgedp[.], xvcmpgtdp[.]
  - xvcmpeqsp[.], xvcmpgesp[.], xvcmpgtsp[.]

Signed-off-by: Tom Musta <tommusta@gmail.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Alexander Graf <agraf@suse.de>

3 files changed, 86 insertions, 0 deletions

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index 8ece96651f..128605ef5a 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -2327,3 +2327,60 @@ VSX_MAX_MIN(xvmaxsp, maxnum, 4, float32, f32)
 VSX_MAX_MIN(xsmindp, minnum, 1, float64, f64)
 VSX_MAX_MIN(xvmindp, minnum, 2, float64, f64)
 VSX_MAX_MIN(xvminsp, minnum, 4, float32, f32)
+
+/* VSX_CMP - VSX floating point compare
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   cmp   - comparison operation
+ *   svxvc - set VXVC bit
+ */
+#define VSX_CMP(op, nels, tp, fld, cmp, svxvc)                            \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                       \
+{                                                                         \
+    ppc_vsr_t xt, xa, xb;                                                 \
+    int i;                                                                \
+    int all_true = 1;                                                     \
+    int all_false = 1;                                                    \
+                                                                          \
+    getVSR(xA(opcode), &xa, env);                                         \
+    getVSR(xB(opcode), &xb, env);                                         \
+    getVSR(xT(opcode), &xt, env);                                         \
+                                                                          \
+    for (i = 0; i < nels; i++) {                                          \
+        if (unlikely(tp##_is_any_nan(xa.fld[i]) ||                        \
+                     tp##_is_any_nan(xb.fld[i]))) {                       \
+            if (tp##_is_signaling_nan(xa.fld[i]) ||                       \
+                tp##_is_signaling_nan(xb.fld[i])) {                       \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);    \
+            }                                                             \
+            if (svxvc) {                                                  \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC, 0);      \
+            }                                                             \
+            xt.fld[i] = 0;                                                \
+            all_true = 0;                                                 \
+        } else {                                                          \
+            if (tp##_##cmp(xb.fld[i], xa.fld[i], &env->fp_status) == 1) { \
+                xt.fld[i] = -1;                                           \
+                all_false = 0;                                            \
+            } else {                                                      \
+                xt.fld[i] = 0;                                            \
+                all_true = 0;                                             \
+            }                                                             \
+        }                                                                 \
+    }                                                                     \
+                                                                          \
+    putVSR(xT(opcode), &xt, env);                                         \
+    if ((opcode >> (31-21)) & 1) {                                        \
+        env->crf[6] = (all_true ? 0x8 : 0) | (all_false ? 0x2 : 0);       \
+    }                                                                     \
+    helper_float_check_status(env);                                       \
+ }
+
+VSX_CMP(xvcmpeqdp, 2, float64, f64, eq, 0)
+VSX_CMP(xvcmpgedp, 2, float64, f64, le, 1)
+VSX_CMP(xvcmpgtdp, 2, float64, f64, lt, 1)
+VSX_CMP(xvcmpeqsp, 4, float32, f32, eq, 0)
+VSX_CMP(xvcmpgesp, 4, float32, f32, le, 1)
+VSX_CMP(xvcmpgtsp, 4, float32, f32, lt, 1)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 4a65d394f3..35389c58bd 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -292,6 +292,9 @@ DEF_HELPER_2(xvnmsubadp, void, env, i32)
 DEF_HELPER_2(xvnmsubmdp, void, env, i32)
 DEF_HELPER_2(xvmaxdp, void, env, i32)
 DEF_HELPER_2(xvmindp, void, env, i32)
+DEF_HELPER_2(xvcmpeqdp, void, env, i32)
+DEF_HELPER_2(xvcmpgedp, void, env, i32)
+DEF_HELPER_2(xvcmpgtdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -312,6 +315,9 @@ DEF_HELPER_2(xvnmsubasp, void, env, i32)
 DEF_HELPER_2(xvnmsubmsp, void, env, i32)
 DEF_HELPER_2(xvmaxsp, void, env, i32)
 DEF_HELPER_2(xvminsp, void, env, i32)
+DEF_HELPER_2(xvcmpeqsp, void, env, i32)
+DEF_HELPER_2(xvcmpgesp, void, env, i32)
+DEF_HELPER_2(xvcmpgtsp, void, env, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index cb68dcdf34..2fae1f32a3 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7345,6 +7345,9 @@ GEN_VSX_HELPER_2(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7365,6 +7368,9 @@ GEN_VSX_HELPER_2(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10014,6 +10020,17 @@ GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2), \
 GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 2, opc3, 0, PPC_NONE, fl2), \
 GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 3, opc3, 0, PPC_NONE, fl2)
 
+#undef GEN_XX3_RC_FORM
+#define GEN_XX3_RC_FORM(name, opc2, opc3, fl2)                          \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x00, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x01, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x02, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x03, opc3 | 0x00, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x00, opc3 | 0x10, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x01, opc3 | 0x10, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x02, opc3 | 0x10, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0x03, opc3 | 0x10, 0, PPC_NONE, fl2)
+
 #undef GEN_XX3FORM_DM
 #define GEN_XX3FORM_DM(name, opc2, opc3) \
 GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x00, opc3|0x00, 0, PPC_NONE, PPC2_VSX),\
@@ -10088,6 +10105,9 @@ GEN_XX3FORM(xvnmsubadp, 0x04, 0x1E, PPC2_VSX),
 GEN_XX3FORM(xvnmsubmdp, 0x04, 0x1F, PPC2_VSX),
 GEN_XX3FORM(xvmaxdp, 0x00, 0x1C, PPC2_VSX),
 GEN_XX3FORM(xvmindp, 0x00, 0x1D, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpeqdp, 0x0C, 0x0C, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgtdp, 0x0C, 0x0D, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgedp, 0x0C, 0x0E, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10108,6 +10128,9 @@ GEN_XX3FORM(xvnmsubasp, 0x04, 0x1A, PPC2_VSX),
 GEN_XX3FORM(xvnmsubmsp, 0x04, 0x1B, PPC2_VSX),
 GEN_XX3FORM(xvmaxsp, 0x00, 0x18, PPC2_VSX),
 GEN_XX3FORM(xvminsp, 0x00, 0x19, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpeqsp, 0x0C, 0x08, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgtsp, 0x0C, 0x09, PPC2_VSX),
+GEN_XX3_RC_FORM(xvcmpgesp, 0x0C, 0x0A, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \