Patchwork [V4,14/22] target-ppc: Add VSX ISA2.06 xtdiv Instructions

login
register
mail settings
Submitter Tom Musta
Date Dec. 18, 2013, 8:19 p.m.
Message ID <1387397961-4894-15-git-send-email-tommusta@gmail.com>
Download mbox | patch
Permalink /patch/303041/
State New
Headers show

Comments

Tom Musta - Dec. 18, 2013, 8:19 p.m.
This patch adds the VSX floating point test for software divide
instructions defined by V2.06 of the PowerPC ISA: xstdivdp, xvtdivdp,
and xvtdivsp.

V2: added ppc_float*_get_unbiased_exp() routines (pulled back from
softfloat).  Eliminated dependency on float*_is_denormalized()
routines.

Signed-off-by: Tom Musta <tommusta@gmail.com>
Reviewed-by: Richard Henderson <address@hidden>
---
 target-ppc/fpu_helper.c |   67 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 ++
 target-ppc/translate.c  |    6 ++++
 3 files changed, 76 insertions(+), 0 deletions(-)

Patch

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index 31669f1..ee03942 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -2028,3 +2028,70 @@  void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
 VSX_RSQRTE(xsrsqrtedp, 1, float64, f64, 1)
 VSX_RSQRTE(xvrsqrtedp, 2, float64, f64, 0)
 VSX_RSQRTE(xvrsqrtesp, 4, float32, f32, 0)
+
+static inline int ppc_float32_get_unbiased_exp(float32 f)
+{
+    return ((f >> 23) & 0xFF) - 127;
+}
+
+static inline int ppc_float64_get_unbiased_exp(float64 f)
+{
+    return ((f >> 52) & 0x7FF) - 1023;
+}
+
+/* VSX_TDIV - VSX floating point test for divide
+ *   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_TDIV(op, nels, tp, fld, emin, emax, 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(xa.fld[i]) ||                     \
+                     tp##_is_infinity(xb.fld[i]) ||                     \
+                     tp##_is_zero(xb.fld[i]))) {                        \
+            fe_flag = 1;                                                \
+            fg_flag = 1;                                                \
+        } else {                                                        \
+            int e_a = ppc_##tp##_get_unbiased_exp(xa.fld[i]);           \
+            int e_b = ppc_##tp##_get_unbiased_exp(xb.fld[i]);           \
+                                                                        \
+            if (unlikely(tp##_is_any_nan(xa.fld[i]) ||                  \
+                         tp##_is_any_nan(xb.fld[i]))) {                 \
+                fe_flag = 1;                                            \
+            } else if ((e_b <= emin) || (e_b >= (emax-2))) {            \
+                fe_flag = 1;                                            \
+            } else if (!tp##_is_zero(xa.fld[i]) &&                      \
+                       (((e_a - e_b) >= emax) ||                        \
+                        ((e_a - e_b) <= (emin+1)) ||                    \
+                         (e_a <= (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 */     \
+                /* so must be denormalized.                      */     \
+                fg_flag = 1;                                            \
+            }                                                           \
+        }                                                               \
+    }                                                                   \
+                                                                        \
+    env->crf[BF(opcode)] = 0x8 | (fg_flag ? 4 : 0) | (fe_flag ? 2 : 0); \
+}
+
+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)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index 4d5e31b..80cffc9 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -258,6 +258,7 @@  DEF_HELPER_2(xsdivdp, void, env, i32)
 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(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -266,6 +267,7 @@  DEF_HELPER_2(xvdivdp, void, env, i32)
 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(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -274,6 +276,7 @@  DEF_HELPER_2(xvdivsp, void, env, i32)
 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(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index 287b924..9a0b36c 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7302,6 +7302,7 @@  GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
 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(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7310,6 +7311,7 @@  GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
 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(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7318,6 +7320,7 @@  GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
 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)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10008,6 +10011,7 @@  GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
 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_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10016,6 +10020,7 @@  GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
 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_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10024,6 +10029,7 @@  GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
 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),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \