[Qemu-ppc] [PATCH V2 12/19] Add VSX ISA2.06 xtsqrt Instructions

[Tom Musta]

This patch adds the VSX floating point test for software square
root instructions defined by V2.06 of the PowerPC ISA: xstsqrtdp,
xvtsqrtdp, xvtsqrtsp.

V2: (a) using locally implemented ppc_float*_get_unbiased_exp
routines  (b) eliminated dependency on float*_is_denormal().

Signed-off-by: Tom Musta <address@hidden>
---
 target-ppc/fpu_helper.c |   54 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 ++
 target-ppc/translate.c  |    6 +++++
 3 files changed, 63 insertions(+), 0 deletions(-)

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index ee03942..73227b7 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -2095,3 +2095,57 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)      
               \
 VSX_TDIV(xstdivdp, 1, float64, f64, -1022, 1023, 52)
 VSX_TDIV(xvtdivdp, 2, float64, f64, -1022, 1023, 52)
 VSX_TDIV(xvtdivsp, 4, float32, f32, -126, 127, 23)
+
+/* VSX_TSQRT - VSX floating point test for square root
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   emin  - minimum unbiased exponent
+ *   emax  - maximum unbiased exponent
+ *   nbits - number of fraction bits
+ */
+#define VSX_TSQRT(op, nels, tp, fld, emin, nbits)                       \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                     \
+{                                                                       \
+    ppc_vsr_t xa, xb;                                                   \
+    int i;                                                              \
+    int fe_flag = 0;                                                    \
+    int fg_flag = 0;                                                    \
+                                                                        \
+    getVSR(xA(opcode), &xa, env);                                       \
+    getVSR(xB(opcode), &xb, env);                                       \
+                                                                        \
+    for (i = 0; i < nels; i++) {                                        \
+        if (unlikely(tp##_is_infinity(xb.fld[i]) ||                     \
+                     tp##_is_zero(xb.fld[i]))) {                        \
+            fe_flag = 1;                                                \
+            fg_flag = 1;                                                \
+        } else {                                                        \
+            int e_b = ppc_##tp##_get_unbiased_exp(xb.fld[i]);           \
+                                                                        \
+            if (unlikely(tp##_is_any_nan(xb.fld[i]))) {                 \
+                fe_flag = 1;                                            \
+            } else if (unlikely(tp##_is_zero(xb.fld[i]))) {             \
+                fe_flag = 1;                                            \
+            } else if (unlikely(tp##_is_neg(xb.fld[i]))) {              \
+                fe_flag = 1;                                            \
+            } else if (!tp##_is_zero(xb.fld[i]) &&                      \
+                      (e_b <= (emin+nbits))) {                          \
+                fe_flag = 1;                                            \
+            }                                                           \
+                                                                        \
+            if (unlikely(tp##_is_zero_or_denormal(xb.fld[i]))) {        \
+                /* XB is not zero because of the above check and */     \
+                /* therefore must be denormalized.               */     \
+                fg_flag = 1;                                            \
+            }                                                           \
+        }                                                               \
+    }                                                                   \
+                                                                        \
+    env->crf[BF(opcode)] = 0x8 | (fg_flag ? 4 : 0) | (fe_flag ? 2 : 0); \
+}
+
+VSX_TSQRT(xstsqrtdp, 1, float64, f64, -1022, 52)
+VSX_TSQRT(xvtsqrtdp, 2, float64, f64, -1022, 52)
+VSX_TSQRT(xvtsqrtsp, 4, float32, f32, -126, 23)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 80cffc9..c413c98 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -259,6 +259,7 @@ DEF_HELPER_2(xsredp, void, env, i32)
 DEF_HELPER_2(xssqrtdp, void, env, i32)
 DEF_HELPER_2(xsrsqrtedp, void, env, i32)
 DEF_HELPER_2(xstdivdp, void, env, i32)
+DEF_HELPER_2(xstsqrtdp, void, env, i32)

 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -268,6 +269,7 @@ DEF_HELPER_2(xvredp, void, env, i32)
 DEF_HELPER_2(xvsqrtdp, void, env, i32)
 DEF_HELPER_2(xvrsqrtedp, void, env, i32)
 DEF_HELPER_2(xvtdivdp, void, env, i32)
+DEF_HELPER_2(xvtsqrtdp, void, env, i32)

 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -277,6 +279,7 @@ DEF_HELPER_2(xvresp, void, env, i32)
 DEF_HELPER_2(xvsqrtsp, void, env, i32)
 DEF_HELPER_2(xvrsqrtesp, void, env, i32)
 DEF_HELPER_2(xvtdivsp, void, env, i32)
+DEF_HELPER_2(xvtsqrtsp, 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 9a0b36c..f1935c7 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7303,6 +7303,7 @@ GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)

 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7312,6 +7313,7 @@ GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)

 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7321,6 +7323,7 @@ GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)

 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10012,6 +10015,7 @@ GEN_XX2FORM(xsredp,  0x14, 0x05, PPC2_VSX),
 GEN_XX2FORM(xssqrtdp,  0x16, 0x04, PPC2_VSX),
 GEN_XX2FORM(xsrsqrtedp,  0x14, 0x04, PPC2_VSX),
 GEN_XX3FORM(xstdivdp,  0x14, 0x07, PPC2_VSX),
+GEN_XX2FORM(xstsqrtdp,  0x14, 0x06, PPC2_VSX),

 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10021,6 +10025,7 @@ GEN_XX2FORM(xvredp,  0x14, 0x0D, PPC2_VSX),
 GEN_XX2FORM(xvsqrtdp,  0x16, 0x0C, PPC2_VSX),
 GEN_XX2FORM(xvrsqrtedp,  0x14, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvtdivdp, 0x14, 0x0F, PPC2_VSX),
+GEN_XX2FORM(xvtsqrtdp, 0x14, 0x0E, PPC2_VSX),

 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10030,6 +10035,7 @@ GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
 GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),
 GEN_XX2FORM(xvrsqrtesp, 0x14, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvtdivsp, 0x14, 0x0B, PPC2_VSX),
+GEN_XX2FORM(xvtsqrtsp, 0x14, 0x0A, PPC2_VSX),

 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
--
1.7.1