target/ppc: Use non-arithmetic conversions for fp load/store

Memory operations have no side effects on fp state.
The use of a "real" conversions between float64 and float32
would raise exceptions for SNaN and out-of-range inputs.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

3 files changed, 61 insertions, 30 deletions

diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 5af5241ab0..b9bb1b856e 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -47,24 +47,61 @@ static inline bool fp_exceptions_enabled(CPUPPCState *env)
 
 /*****************************************************************************/
 /* Floating point operations helpers */
-uint64_t helper_float32_to_float64(CPUPPCState *env, uint32_t arg)
+
+/*
+ * This is the non-arithmatic conversion that happens e.g. on loads.
+ * In the Power ISA pseudocode, this is called DOUBLE.
+ */
+uint64_t helper_todouble(uint32_t arg)
 {
-    CPU_FloatU f;
-    CPU_DoubleU d;
+    uint32_t abs_arg = arg & 0x7fffffff;
+    uint64_t ret;
 
-    f.l = arg;
-    d.d = float32_to_float64(f.f, &env->fp_status);
-    return d.ll;
+    if (likely(abs_arg >= 0x00800000)) {
+        /* Normalized operand, or Inf, or NaN.  */
+        ret  = (uint64_t)extract32(arg, 30, 2) << 62;
+        ret |= ((extract32(arg, 30, 1) ^ 1) * (uint64_t)7) << 59;
+        ret |= (uint64_t)extract32(arg, 0, 30) << 29;
+    } else {
+        /* Zero or Denormalized operand.  */
+        ret = (uint64_t)extract32(arg, 31, 1) << 63;
+        if (unlikely(abs_arg != 0)) {
+            /* Denormalized operand.  */
+            int shift = clz32(abs_arg) - 9;
+            int exp = -126 - shift + 1023;
+            ret |= (uint64_t)exp << 52;
+            ret |= abs_arg << (shift + 29);
+        }
+    }
+    return ret;
 }
 
-uint32_t helper_float64_to_float32(CPUPPCState *env, uint64_t arg)
+/*
+ * This is the non-arithmatic conversion that happens e.g. on stores.
+ * In the Power ISA pseudocode, this is called SINGLE.
+ */
+uint32_t helper_tosingle(uint64_t arg)
 {
-    CPU_FloatU f;
-    CPU_DoubleU d;
+    int exp = extract64(arg, 52, 11);
+    uint32_t ret;
 
-    d.ll = arg;
-    f.f = float64_to_float32(d.d, &env->fp_status);
-    return f.l;
+    if (likely(exp > 896)) {
+        /* No denormalization required (includes Inf, NaN).  */
+        ret  = extract64(arg, 62, 2) << 30;
+        ret |= extract64(arg, 29, 30);
+    } else {
+        /* Zero or Denormal result.  If the exponent is in bounds for
+         * a single-precision denormal result, extract the proper bits.
+         * If the input is not zero, and the exponent is out of bounds,
+         * then the result is undefined; this underflows to zero.
+         */
+        ret = extract64(arg, 63, 1) << 31;
+        if (unlikely(exp >= 874)) {
+            /* Denormal result.  */
+            ret |= ((1ULL << 52) | extract64(arg, 0, 52)) >> (896 + 30 - exp);
+        }
+    }
+    return ret;
 }
 
 static inline int ppc_float32_get_unbiased_exp(float32 f)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 7ed72c2337..ef64248bc4 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -61,8 +61,8 @@ DEF_HELPER_2(compute_fprf_float64, void, env, i64)
 DEF_HELPER_3(store_fpscr, void, env, i64, i32)
 DEF_HELPER_2(fpscr_clrbit, void, env, i32)
 DEF_HELPER_2(fpscr_setbit, void, env, i32)
-DEF_HELPER_2(float64_to_float32, i32, env, i64)
-DEF_HELPER_2(float32_to_float64, i64, env, i32)
+DEF_HELPER_FLAGS_1(todouble, TCG_CALL_NO_RWG_SE, i64, i32)
+DEF_HELPER_FLAGS_1(tosingle, TCG_CALL_NO_RWG_SE, i32, i64)
 
 DEF_HELPER_4(fcmpo, void, env, i64, i64, i32)
 DEF_HELPER_4(fcmpu, void, env, i64, i64, i32)
diff --git a/target/ppc/translate/fp-impl.inc.c b/target/ppc/translate/fp-impl.inc.c
index 2fbd4d4f38..a6f522b85c 100644
--- a/target/ppc/translate/fp-impl.inc.c
+++ b/target/ppc/translate/fp-impl.inc.c
@@ -660,15 +660,12 @@ GEN_LDUF(name, ldop, op | 0x21, type);                                        \
 GEN_LDUXF(name, ldop, op | 0x01, type);                                       \
 GEN_LDXF(name, ldop, 0x17, op | 0x00, type)
 
-static inline void gen_qemu_ld32fs(DisasContext *ctx, TCGv_i64 arg1, TCGv arg2)
+static void gen_qemu_ld32fs(DisasContext *ctx, TCGv_i64 dest, TCGv addr)
 {
-    TCGv t0 = tcg_temp_new();
-    TCGv_i32 t1 = tcg_temp_new_i32();
-    gen_qemu_ld32u(ctx, t0, arg2);
-    tcg_gen_trunc_tl_i32(t1, t0);
-    tcg_temp_free(t0);
-    gen_helper_float32_to_float64(arg1, cpu_env, t1);
-    tcg_temp_free_i32(t1);
+    TCGv_i32 tmp = tcg_temp_new_i32();
+    tcg_gen_qemu_ld_i32(tmp, addr, ctx->mem_idx, DEF_MEMOP(MO_UL));
+    gen_helper_todouble(dest, tmp);
+    tcg_temp_free_i32(tmp);
 }
 
  /* lfd lfdu lfdux lfdx */
@@ -836,15 +833,12 @@ GEN_STUF(name, stop, op | 0x21, type);                                        \
 GEN_STUXF(name, stop, op | 0x01, type);                                       \
 GEN_STXF(name, stop, 0x17, op | 0x00, type)
 
-static inline void gen_qemu_st32fs(DisasContext *ctx, TCGv_i64 arg1, TCGv arg2)
+static void gen_qemu_st32fs(DisasContext *ctx, TCGv_i64 src, TCGv addr)
 {
-    TCGv_i32 t0 = tcg_temp_new_i32();
-    TCGv t1 = tcg_temp_new();
-    gen_helper_float64_to_float32(t0, cpu_env, arg1);
-    tcg_gen_extu_i32_tl(t1, t0);
-    tcg_temp_free_i32(t0);
-    gen_qemu_st32(ctx, t1, arg2);
-    tcg_temp_free(t1);
+    TCGv_i32 tmp = tcg_temp_new_i32();
+    gen_helper_tosingle(tmp, src);
+    tcg_gen_qemu_st_i32(tmp, addr, ctx->mem_idx, DEF_MEMOP(MO_UL));
+    tcg_temp_free_i32(tmp);
 }
 
 /* stfd stfdu stfdux stfdx */