target/ppc: Moved XVTSTDC[DS]P to decodetree

Moved XVTSTDCSP and XVTSTDCDP to decodetree an restructured the helper
to be simpler and do all decoding in the decodetree (so XB, XT and DCMX
are all calculated outside the helper).

Obs: The tests in this one are slightly different, these are the sum of
these instructions with all possible immediate and those instructions
are repeated 10 times.

xvtstdcsp:
rept    loop    master             patch
8       12500   2,76402100         2,70699100 (-2.1%)
25      4000    2,64867100         2,67884100 (+1.1%)
100     1000    2,73806300         2,78701000 (+1.8%)
500     200     3,44666500         3,61027600 (+4.7%)
2500    40      5,85790200         6,47475500 (+10.5%)
8000    12     15,22102100        17,46062900 (+14.7%)

xvtstdcdp:
rept    loop    master             patch
8       12500   2,11818000         1,61065300 (-24.0%)
25      4000    2,04573400         1,60132200 (-21.7%)
100     1000    2,13834100         1,69988100 (-20.5%)
500     200     2,73977000         2,48631700 (-9.3%)
2500    40      5,05067000         5,25914100 (+4.1%)
8000    12     14,60507800        15,93704900 (+9.1%)

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20221019125040.48028-11-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>

diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index ae25f32d6e9a97b4f11045d2f654d8b11fc17c5c..960a76a8a523996d75d8bcb943ee5eaf3a83a295 100644 (file)
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -3295,11 +3295,46 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)         \
     }                                                       \
 }
 
-VSX_TEST_DC(xvtstdcdp, 2, xB(opcode), float64, VsrD(i), VsrD(i), UINT64_MAX, 0)
-VSX_TEST_DC(xvtstdcsp, 4, xB(opcode), float32, VsrW(i), VsrW(i), UINT32_MAX, 0)
 VSX_TEST_DC(xststdcdp, 1, xB(opcode), float64, VsrD(0), VsrD(0), 0, 1)
 VSX_TEST_DC(xststdcqp, 1, (rB(opcode) + 32), float128, f128, VsrD(0), 0, 1)
 
+#define VSX_TSTDC(tp)                                       \
+static int32_t tp##_tstdc(tp b, uint32_t dcmx)              \
+{                                                           \
+    uint32_t match = 0;                                     \
+    uint32_t sign = tp##_is_neg(b);                         \
+    if (tp##_is_any_nan(b)) {                               \
+        match = extract32(dcmx, 6, 1);                      \
+    } else if (tp##_is_infinity(b)) {                       \
+        match = extract32(dcmx, 4 + !sign, 1);              \
+    } else if (tp##_is_zero(b)) {                           \
+        match = extract32(dcmx, 2 + !sign, 1);              \
+    } else if (tp##_is_zero_or_denormal(b)) {               \
+        match = extract32(dcmx, 0 + !sign, 1);              \
+    }                                                       \
+    return (match != 0);                                    \
+}
+
+VSX_TSTDC(float32)
+VSX_TSTDC(float64)
+#undef VSX_TSTDC
+
+void helper_XVTSTDCDP(ppc_vsr_t *t, ppc_vsr_t *b, uint64_t dcmx, uint32_t v)
+{
+    int i;
+    for (i = 0; i < 2; i++) {
+        t->s64[i] = (int64_t)-float64_tstdc(b->f64[i], dcmx);
+    }
+}
+
+void helper_XVTSTDCSP(ppc_vsr_t *t, ppc_vsr_t *b, uint64_t dcmx, uint32_t v)
+{
+    int i;
+    for (i = 0; i < 4; i++) {
+        t->s32[i] = (int32_t)-float32_tstdc(b->f32[i], dcmx);
+    }
+}
+
 void helper_xststdcsp(CPUPPCState *env, uint32_t opcode, ppc_vsr_t *xb)
 {
     uint32_t dcmx, sign, exp;

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index fd8280dfa7c964dd741c01537aab6c0dd826c992..9e5d11939ba4fbd7463c9c63d53dee9eb0bf53f0 100644 (file)
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -517,8 +517,8 @@ DEF_HELPER_3(xvcvsxdsp, void, env, vsr, vsr)
 DEF_HELPER_3(xvcvuxdsp, void, env, vsr, vsr)
 DEF_HELPER_3(xvcvsxwsp, void, env, vsr, vsr)
 DEF_HELPER_3(xvcvuxwsp, void, env, vsr, vsr)
-DEF_HELPER_2(xvtstdcsp, void, env, i32)
-DEF_HELPER_2(xvtstdcdp, void, env, i32)
+DEF_HELPER_FLAGS_4(XVTSTDCSP, TCG_CALL_NO_RWG, void, vsr, vsr, i64, i32)
+DEF_HELPER_FLAGS_4(XVTSTDCDP, TCG_CALL_NO_RWG, void, vsr, vsr, i64, i32)
 DEF_HELPER_3(xvrspi, void, env, vsr, vsr)
 DEF_HELPER_3(xvrspic, void, env, vsr, vsr)
 DEF_HELPER_3(xvrspim, void, env, vsr, vsr)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 3594c0c9607fed34b40c033fb2950d85bda8e48e..44905edd29327423341f3ea908faf2a2775d8922 100644 (file)
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -199,6 +199,9 @@
 
 @XX2_uim4       ...... ..... . uim:4 ..... ......... ..         &XX2_uim xt=%xx_xt xb=%xx_xb
 
+%xx_uim7        6:1 2:1 16:5
+@XX2_uim7       ...... ..... ..... ..... .... . ... . ..        &XX2_uim xt=%xx_xt xb=%xx_xb uim=%xx_uim7
+
 &XX2_bf_xb      bf xb
 @XX2_bf_xb      ...... bf:3 .. ..... ..... ......... . .        &XX2_bf_xb xb=%xx_xb
 
@@ -848,6 +851,8 @@ XSCVSPDPN       111100 ..... ----- ..... 101001011 ..   @XX2
 ## VSX Binary Floating-Point Math Support Instructions
 
 XVXSIGSP        111100 ..... 01001 ..... 111011011 ..   @XX2
+XVTSTDCDP       111100 ..... ..... ..... 1111 . 101 ... @XX2_uim7
+XVTSTDCSP       111100 ..... ..... ..... 1101 . 101 ... @XX2_uim7
 
 ## VSX Vector Test Least-Significant Bit by Byte Instruction
 

diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc
index 1c289238ecbd16d0345f41b1b08e744df5495d66..287ea8e2ced066bbae5571dd4b2332bebe2ed7a4 100644 (file)
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -630,6 +630,8 @@ static void gen_mtvsrws(DisasContext *ctx)
 #define OP_CPSGN 4
 #define SGN_MASK_DP  0x8000000000000000ull
 #define SGN_MASK_SP 0x8000000080000000ull
+#define EXP_MASK_DP  0x7FF0000000000000ull
+#define EXP_MASK_SP 0x7F8000007F800000ull
 
 #define VSX_SCALAR_MOVE(name, op, sgn_mask)                       \
 static void glue(gen_, name)(DisasContext *ctx)                   \
@@ -1110,6 +1112,30 @@ GEN_VSX_HELPER_X2(xscvhpdp, 0x16, 0x15, 0x10, PPC2_ISA300)
 GEN_VSX_HELPER_R2(xscvsdqp, 0x04, 0x1A, 0x0A, PPC2_ISA300)
 GEN_VSX_HELPER_X2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX)
 
+static bool do_xvtstdc(DisasContext *ctx, arg_XX2_uim *a, unsigned vece)
+{
+    static const GVecGen2i op[] = {
+        {
+            .fnoi = gen_helper_XVTSTDCSP,
+            .vece = MO_32
+        },
+        {
+            .fnoi = gen_helper_XVTSTDCDP,
+            .vece = MO_64
+        },
+    };
+
+    REQUIRE_VSX(ctx);
+
+    tcg_gen_gvec_2i(vsr_full_offset(a->xt), vsr_full_offset(a->xb),
+                    16, 16, (int32_t)(a->uim), &op[vece - MO_32]);
+
+    return true;
+}
+
+TRANS_FLAGS2(VSX, XVTSTDCSP, do_xvtstdc, MO_32)
+TRANS_FLAGS2(VSX, XVTSTDCDP, do_xvtstdc, MO_64)
+
 bool trans_XSCVSPDPN(DisasContext *ctx, arg_XX2 *a)
 {
     TCGv_i64 tmp;
@@ -1213,8 +1239,6 @@ GEN_VSX_HELPER_X2(xvrspic, 0x16, 0x0A, 0, PPC2_VSX)
 GEN_VSX_HELPER_X2(xvrspim, 0x12, 0x0B, 0, PPC2_VSX)
 GEN_VSX_HELPER_X2(xvrspip, 0x12, 0x0A, 0, PPC2_VSX)
 GEN_VSX_HELPER_X2(xvrspiz, 0x12, 0x09, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvtstdcsp, 0x14, 0x1A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvtstdcdp, 0x14, 0x1E, 0, PPC2_VSX)
 
 static bool trans_XXPERM(DisasContext *ctx, arg_XX3 *a)
 {

diff --git a/target/ppc/translate/vsx-ops.c.inc b/target/ppc/translate/vsx-ops.c.inc
index f7d7377379f3183af4b5e66818c8f26f92e7bca5..4b317d4b06d234151e796785e269dcfb450d275b 100644 (file)
--- a/target/ppc/translate/vsx-ops.c.inc
+++ b/target/ppc/translate/vsx-ops.c.inc
@@ -157,14 +157,6 @@ GEN_XX2FORM_EO(xvxexpdp, 0x16, 0x1D, 0x00, PPC2_ISA300),
 GEN_XX2FORM_EO(xvxsigdp, 0x16, 0x1D, 0x01, PPC2_ISA300),
 GEN_XX2FORM_EO(xvxexpsp, 0x16, 0x1D, 0x08, PPC2_ISA300),
 
-/* DCMX  =  bit[25] << 6 | bit[29] << 5 | bit[11:15] */
-#define GEN_XX2FORM_DCMX(name, opc2, opc3, fl2) \
-GEN_XX3FORM(name, opc2, opc3 | 0, fl2),         \
-GEN_XX3FORM(name, opc2, opc3 | 1, fl2)
-
-GEN_XX2FORM_DCMX(xvtstdcdp, 0x14, 0x1E, PPC2_ISA300),
-GEN_XX2FORM_DCMX(xvtstdcsp, 0x14, 0x1A, PPC2_ISA300),
-
 GEN_XX3FORM(xsadddp, 0x00, 0x04, PPC2_VSX),
 GEN_VSX_XFORM_300(xsaddqp, 0x04, 0x00, 0x0),
 GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX),