This patch adds the VSX floating point maximum and minimum
instructions:
- xsmaxdp, xvmaxdp, xvmaxsp
- xsmindp, xvmindp, xvminsp
Because of the Power ISA definitions of maximum and minimum
on various boundary cases, the standard softfloat comparison
routines (e.g. float64_lt) do not work as well as one might
think. Therefore specific routines for comparing 64 and 32
bit floating point numbers are implemented in the PowerPC
helper code.
Signed-off-by: Tom Musta <tommu...@gmail.com>
Reviewed-by: Richard Henderson <address@hidden>
---
V2: consolidated into a single macro, using the softfloat
float*_max/float*_min routines.
V5: Simplified implementation with new maxnum/minnum support
in softfloat.
target-ppc/fpu_helper.c | 39 +++++++++++++++++++++++++++++++++++++++
target-ppc/helper.h | 6 ++++++
target-ppc/translate.c | 12 ++++++++++++
3 files changed, 57 insertions(+), 0 deletions(-)
diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index eb5d878..8ece966 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -2288,3 +2288,42 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)
\
VSX_SCALAR_CMP(xscmpodp, 1)
VSX_SCALAR_CMP(xscmpudp, 0)
+
+#define float64_snan_to_qnan(x) ((x) | 0x0008000000000000ul)
+#define float32_snan_to_qnan(x) ((x) | 0x00400000)
+
+/* VSX_MAX_MIN - VSX floating point maximum/minimum
+ * name - instruction mnemonic
+ * op - operation (max or min)
+ * nels - number of elements (1, 2 or 4)
+ * tp - type (float32 or float64)
+ * fld - vsr_t field (f32 or f64)
+ */
+#define VSX_MAX_MIN(name, op, nels, tp, fld) \
+void helper_##name(CPUPPCState *env, uint32_t opcode) \
+{ \
+ ppc_vsr_t xt, xa, xb; \
+ int i; \
+ \
+ getVSR(xA(opcode), &xa, env); \
+ getVSR(xB(opcode), &xb, env); \
+ getVSR(xT(opcode), &xt, env); \
+ \
+ for (i = 0; i < nels; i++) { \
+ xt.fld[i] = tp##_##op(xa.fld[i], xb.fld[i], &env->fp_status); \
+ if (unlikely(tp##_is_signaling_nan(xa.fld[i]) || \
+ tp##_is_signaling_nan(xb.fld[i]))) { \
+ fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \
+ } \
+ } \
+ \
+ putVSR(xT(opcode), &xt, env); \
+ helper_float_check_status(env); \
+}
+
+VSX_MAX_MIN(xsmaxdp, maxnum, 1, float64, f64)
+VSX_MAX_MIN(xvmaxdp, maxnum, 2, float64, f64)
+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)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index cd72388..4a65d39 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -270,6 +270,8 @@ DEF_HELPER_2(xsnmsubadp, void, env, i32)
DEF_HELPER_2(xsnmsubmdp, void, env, i32)
DEF_HELPER_2(xscmpodp, void, env, i32)
DEF_HELPER_2(xscmpudp, void, env, i32)
+DEF_HELPER_2(xsmaxdp, void, env, i32)
+DEF_HELPER_2(xsmindp, void, env, i32)
DEF_HELPER_2(xvadddp, void, env, i32)
DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -288,6 +290,8 @@ DEF_HELPER_2(xvnmaddadp, void, env, i32)
DEF_HELPER_2(xvnmaddmdp, void, env, i32)
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(xvaddsp, void, env, i32)
DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -306,6 +310,8 @@ DEF_HELPER_2(xvnmaddasp, void, env, i32)
DEF_HELPER_2(xvnmaddmsp, void, env, i32)
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(efscfsi, i32, env, i32)
DEF_HELPER_2(efscfui, i32, env, i32)
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index 9325a4c..5cf2335 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7323,6 +7323,8 @@ GEN_VSX_HELPER_2(xsnmsubadp, 0x04, 0x16, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsnmsubmdp, 0x04, 0x17, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7341,6 +7343,8 @@ GEN_VSX_HELPER_2(xvnmaddadp, 0x04, 0x1C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvnmaddmdp, 0x04, 0x1D, 0, PPC2_VSX)
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(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7359,6 +7363,8 @@ GEN_VSX_HELPER_2(xvnmaddasp, 0x04, 0x18, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvnmaddmsp, 0x04, 0x19, 0, PPC2_VSX)
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)
#define VSX_LOGICAL(name, tcg_op) \
static void glue(gen_, name)(DisasContext * ctx) \
@@ -10060,6 +10066,8 @@ GEN_XX3FORM(xsnmsubadp, 0x04, 0x16, PPC2_VSX),
GEN_XX3FORM(xsnmsubmdp, 0x04, 0x17, PPC2_VSX),
GEN_XX2FORM(xscmpodp, 0x0C, 0x05, PPC2_VSX),
GEN_XX2FORM(xscmpudp, 0x0C, 0x04, PPC2_VSX),
+GEN_XX3FORM(xsmaxdp, 0x00, 0x14, PPC2_VSX),
+GEN_XX3FORM(xsmindp, 0x00, 0x15, PPC2_VSX),
GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10078,6 +10086,8 @@ GEN_XX3FORM(xvnmaddadp, 0x04, 0x1C, PPC2_VSX),
GEN_XX3FORM(xvnmaddmdp, 0x04, 0x1D, PPC2_VSX),
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_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10096,6 +10106,8 @@ GEN_XX3FORM(xvnmaddasp, 0x04, 0x18, PPC2_VSX),
GEN_XX3FORM(xvnmaddmsp, 0x04, 0x19, PPC2_VSX),
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),
#undef VSX_LOGICAL
#define VSX_LOGICAL(name, opc2, opc3, fl2) \
--
1.7.1
