Patchwork [V4,21/22] target-ppc: Add VSX ISA2.06 Integer Conversion Instructions

login
register
mail settings
Submitter Tom Musta
Date Dec. 18, 2013, 8:19 p.m.
Message ID <1387397961-4894-22-git-send-email-tommusta@gmail.com>
Download mbox | patch
Permalink /patch/303044/
State New
Headers show

Comments

Tom Musta - Dec. 18, 2013, 8:19 p.m.
This patch adds the VSX Integer Conversion instructions defined by
V2.06 of the PowerPC ISA:

  - xscvdpsxds, xscvdpsxws, xscvdpuxds, xscvdpuxws
  - xvcvdpsxds, xvcvdpsxws, xvcvdpuxds, xvcvdpuxws
  - xvcvspsxds, xvcvspsxws, xvcvspuxds, xvcvspuxws
  - xscvsxddp, xscvuxddp
  - xvcvsxddp, xscvsxwdp, xvcvuxddp, xvcvuxwdp
  - xvcvsxdsp, xscvsxwsp, xvcvuxdsp, xvcvuxwsp

Signed-off-by: Tom Musta <tommusta@gmail.com>
Reviewed-by: Richard Henderson <address@hidden>
---
 target-ppc/fpu_helper.c |  107 +++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |   22 ++++++++++
 target-ppc/translate.c  |   44 +++++++++++++++++++
 3 files changed, 173 insertions(+), 0 deletions(-)

Patch

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index c9fb59f..f913ad7 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -2441,3 +2441,110 @@  VSX_CVT_FP_TO_FP(xscvdpsp, 1, float64, float32, f64[i], f32[j], 1)
 VSX_CVT_FP_TO_FP(xscvspdp, 1, float32, float64, f32[j], f64[i], 1)
 VSX_CVT_FP_TO_FP(xvcvdpsp, 2, float64, float32, f64[i], f32[j], 0)
 VSX_CVT_FP_TO_FP(xvcvspdp, 2, float32, float64, f32[j], f64[i], 0)
+
+/* VSX_CVT_FP_TO_INT - VSX floating point to integer conversion
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   stp   - source type (float32 or float64)
+ *   ttp   - target type (int32, uint32, int64 or uint64)
+ *   sfld  - source vsr_t field
+ *   tfld  - target vsr_t field
+ *   jdef  - definition of the j index (i or 2*i)
+ *   rnan  - resulting NaN
+ */
+#define VSX_CVT_FP_TO_INT(op, nels, stp, ttp, sfld, tfld, jdef, rnan)        \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
+{                                                                            \
+    ppc_vsr_t xt, xb;                                                        \
+    int i;                                                                   \
+                                                                             \
+    getVSR(xB(opcode), &xb, env);                                            \
+    getVSR(xT(opcode), &xt, env);                                            \
+                                                                             \
+    for (i = 0; i < nels; i++) {                                             \
+        int j = jdef;                                                        \
+        if (unlikely(stp##_is_any_nan(xb.sfld))) {                           \
+            if (stp##_is_signaling_nan(xb.sfld)) {                           \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0);       \
+            }                                                                \
+            fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 0);            \
+            xt.tfld = rnan;                                                  \
+        } else {                                                             \
+            xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status);              \
+            if (env->fp_status.float_exception_flags & float_flag_invalid) { \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 0);        \
+            }                                                                \
+        }                                                                    \
+    }                                                                        \
+                                                                             \
+    putVSR(xT(opcode), &xt, env);                                            \
+    helper_float_check_status(env);                                          \
+}
+
+VSX_CVT_FP_TO_INT(xscvdpsxds, 1, float64, int64, f64[j], u64[i], i, \
+                  0x8000000000000000ul)
+VSX_CVT_FP_TO_INT(xscvdpsxws, 1, float64, int32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0x80000000l)
+VSX_CVT_FP_TO_INT(xscvdpuxds, 1, float64, uint64, f64[j], u64[i], i, 0ul)
+VSX_CVT_FP_TO_INT(xscvdpuxws, 1, float64, uint32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_FP_TO_INT(xvcvdpsxds, 2, float64, int64, f64[j], u64[i], i, \
+                  0x8000000000000000ul)
+VSX_CVT_FP_TO_INT(xvcvdpsxws, 2, float64, int32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0x80000000l)
+VSX_CVT_FP_TO_INT(xvcvdpuxds, 2, float64, uint64, f64[j], u64[i], i, 0ul)
+VSX_CVT_FP_TO_INT(xvcvdpuxws, 2, float64, uint32, f64[i], u32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_FP_TO_INT(xvcvspsxds, 2, float32, int64, f32[j], u64[i], \
+                  2*i + JOFFSET, 0x8000000000000000ul)
+VSX_CVT_FP_TO_INT(xvcvspsxws, 4, float32, int32, f32[j], u32[j], i, \
+                  0x80000000l)
+VSX_CVT_FP_TO_INT(xvcvspuxds, 2, float32, uint64, f32[j], u64[i], \
+                  2*i + JOFFSET, 0ul)
+VSX_CVT_FP_TO_INT(xvcvspuxws, 4, float32, uint32, f32[j], u32[i], i, 0)
+
+/* VSX_CVT_INT_TO_FP - VSX integer to floating point conversion
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   stp   - source type (int32, uint32, int64 or uint64)
+ *   ttp   - target type (float32 or float64)
+ *   sfld  - source vsr_t field
+ *   tfld  - target vsr_t field
+ *   jdef  - definition of the j index (i or 2*i)
+ *   sfprf - set FPRF
+ */
+#define VSX_CVT_INT_TO_FP(op, nels, stp, ttp, sfld, tfld, jdef, sfprf)  \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                     \
+{                                                                       \
+    ppc_vsr_t xt, xb;                                                   \
+    int i;                                                              \
+                                                                        \
+    getVSR(xB(opcode), &xb, env);                                       \
+    getVSR(xT(opcode), &xt, env);                                       \
+                                                                        \
+    for (i = 0; i < nels; i++) {                                        \
+        int j = jdef;                                                   \
+        xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status);             \
+        if (sfprf) {                                                    \
+            helper_compute_fprf(env, xt.tfld, sfprf);                   \
+        }                                                               \
+    }                                                                   \
+                                                                        \
+    putVSR(xT(opcode), &xt, env);                                       \
+    helper_float_check_status(env);                                     \
+}
+
+VSX_CVT_INT_TO_FP(xscvsxddp, 1, int64, float64, u64[j], f64[i], i, 1)
+VSX_CVT_INT_TO_FP(xscvuxddp, 1, uint64, float64, u64[j], f64[i], i, 1)
+VSX_CVT_INT_TO_FP(xvcvsxddp, 2, int64, float64, u64[j], f64[i], i, 0)
+VSX_CVT_INT_TO_FP(xvcvuxddp, 2, uint64, float64, u64[j], f64[i], i, 0)
+VSX_CVT_INT_TO_FP(xvcvsxwdp, 2, int32, float64, u32[j], f64[i], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvuxwdp, 2, uint64, float64, u32[j], f64[i], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvsxdsp, 2, int64, float32, u64[i], f32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvuxdsp, 2, uint64, float32, u64[i], f32[j], \
+                  2*i + JOFFSET, 0)
+VSX_CVT_INT_TO_FP(xvcvsxwsp, 4, int32, float32, u32[j], f32[i], i, 0)
+VSX_CVT_INT_TO_FP(xvcvuxwsp, 4, uint32, float32, u32[j], f32[i], i, 0)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index dd9518c..de46b6f 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -274,6 +274,12 @@  DEF_HELPER_2(xsmaxdp, void, env, i32)
 DEF_HELPER_2(xsmindp, void, env, i32)
 DEF_HELPER_2(xscvdpsp, void, env, i32)
 DEF_HELPER_2(xscvspdp, void, env, i32)
+DEF_HELPER_2(xscvdpsxds, void, env, i32)
+DEF_HELPER_2(xscvdpsxws, void, env, i32)
+DEF_HELPER_2(xscvdpuxds, void, env, i32)
+DEF_HELPER_2(xscvdpuxws, void, env, i32)
+DEF_HELPER_2(xscvsxddp, void, env, i32)
+DEF_HELPER_2(xscvuxddp, void, env, i32)
 
 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
@@ -298,6 +304,14 @@  DEF_HELPER_2(xvcmpeqdp, void, env, i32)
 DEF_HELPER_2(xvcmpgedp, void, env, i32)
 DEF_HELPER_2(xvcmpgtdp, void, env, i32)
 DEF_HELPER_2(xvcvdpsp, void, env, i32)
+DEF_HELPER_2(xvcvdpsxds, void, env, i32)
+DEF_HELPER_2(xvcvdpsxws, void, env, i32)
+DEF_HELPER_2(xvcvdpuxds, void, env, i32)
+DEF_HELPER_2(xvcvdpuxws, void, env, i32)
+DEF_HELPER_2(xvcvsxddp, void, env, i32)
+DEF_HELPER_2(xvcvuxddp, void, env, i32)
+DEF_HELPER_2(xvcvsxwdp, void, env, i32)
+DEF_HELPER_2(xvcvuxwdp, void, env, i32)
 
 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
@@ -322,6 +336,14 @@  DEF_HELPER_2(xvcmpeqsp, void, env, i32)
 DEF_HELPER_2(xvcmpgesp, void, env, i32)
 DEF_HELPER_2(xvcmpgtsp, void, env, i32)
 DEF_HELPER_2(xvcvspdp, void, env, i32)
+DEF_HELPER_2(xvcvspsxds, void, env, i32)
+DEF_HELPER_2(xvcvspsxws, void, env, i32)
+DEF_HELPER_2(xvcvspuxds, void, env, i32)
+DEF_HELPER_2(xvcvspuxws, void, env, i32)
+DEF_HELPER_2(xvcvsxdsp, void, env, i32)
+DEF_HELPER_2(xvcvuxdsp, void, env, i32)
+DEF_HELPER_2(xvcvsxwsp, void, env, i32)
+DEF_HELPER_2(xvcvuxwsp, 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 1366ced..bb36e8f 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7318,6 +7318,12 @@  GEN_VSX_HELPER_2(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvdpsxds, 0x10, 0x15, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvdpsxws, 0x10, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvdpuxds, 0x10, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvdpuxws, 0x10, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvsxddp, 0x10, 0x17, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xscvuxddp, 0x10, 0x16, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
@@ -7342,6 +7348,14 @@  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(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvdpsxds, 0x10, 0x1D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvdpsxws, 0x10, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvdpuxds, 0x10, 0x1C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvdpuxws, 0x10, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvsxddp, 0x10, 0x1F, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvuxddp, 0x10, 0x1E, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvsxwdp, 0x10, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvuxwdp, 0x10, 0x0E, 0, PPC2_VSX)
 
 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
@@ -7366,6 +7380,14 @@  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)
 GEN_VSX_HELPER_2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvspsxds, 0x10, 0x19, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvspsxws, 0x10, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvspuxds, 0x10, 0x18, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvspuxws, 0x10, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvsxdsp, 0x10, 0x1B, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvuxdsp, 0x10, 0x1A, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvsxwsp, 0x10, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvcvuxwsp, 0x10, 0x0A, 0, PPC2_VSX)
 
 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10083,6 +10105,12 @@  GEN_XX3FORM(xsmaxdp, 0x00, 0x14, PPC2_VSX),
 GEN_XX3FORM(xsmindp, 0x00, 0x15, PPC2_VSX),
 GEN_XX2FORM(xscvdpsp, 0x12, 0x10, PPC2_VSX),
 GEN_XX2FORM(xscvspdp, 0x12, 0x14, PPC2_VSX),
+GEN_XX2FORM(xscvdpsxds, 0x10, 0x15, PPC2_VSX),
+GEN_XX2FORM(xscvdpsxws, 0x10, 0x05, PPC2_VSX),
+GEN_XX2FORM(xscvdpuxds, 0x10, 0x14, PPC2_VSX),
+GEN_XX2FORM(xscvdpuxws, 0x10, 0x04, PPC2_VSX),
+GEN_XX2FORM(xscvsxddp, 0x10, 0x17, PPC2_VSX),
+GEN_XX2FORM(xscvuxddp, 0x10, 0x16, PPC2_VSX),
 
 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
@@ -10107,6 +10135,14 @@  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_XX2FORM(xvcvdpsp, 0x12, 0x18, PPC2_VSX),
+GEN_XX2FORM(xvcvdpsxds, 0x10, 0x1D, PPC2_VSX),
+GEN_XX2FORM(xvcvdpsxws, 0x10, 0x0D, PPC2_VSX),
+GEN_XX2FORM(xvcvdpuxds, 0x10, 0x1C, PPC2_VSX),
+GEN_XX2FORM(xvcvdpuxws, 0x10, 0x0C, PPC2_VSX),
+GEN_XX2FORM(xvcvsxddp, 0x10, 0x1F, PPC2_VSX),
+GEN_XX2FORM(xvcvuxddp, 0x10, 0x1E, PPC2_VSX),
+GEN_XX2FORM(xvcvsxwdp, 0x10, 0x0F, PPC2_VSX),
+GEN_XX2FORM(xvcvuxwdp, 0x10, 0x0E, PPC2_VSX),
 
 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
@@ -10131,6 +10167,14 @@  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),
 GEN_XX2FORM(xvcvspdp, 0x12, 0x1C, PPC2_VSX),
+GEN_XX2FORM(xvcvspsxds, 0x10, 0x19, PPC2_VSX),
+GEN_XX2FORM(xvcvspsxws, 0x10, 0x09, PPC2_VSX),
+GEN_XX2FORM(xvcvspuxds, 0x10, 0x18, PPC2_VSX),
+GEN_XX2FORM(xvcvspuxws, 0x10, 0x08, PPC2_VSX),
+GEN_XX2FORM(xvcvsxdsp, 0x10, 0x1B, PPC2_VSX),
+GEN_XX2FORM(xvcvuxdsp, 0x10, 0x1A, PPC2_VSX),
+GEN_XX2FORM(xvcvsxwsp, 0x10, 0x0B, PPC2_VSX),
+GEN_XX2FORM(xvcvuxwsp, 0x10, 0x0A, PPC2_VSX),
 
 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \