target/ppc: Move VNEG[WD] to decodtree and use gvec

Moved the instructions VNEGW and VNEGD to decodetree and used gvec to
decode it.

vnegw:
rept    loop    master             patch
8       12500   0,01053200         0,00548400 (-47.9%)
25      4000    0,01030500         0,00390000 (-62.2%)
100     1000    0,01096300         0,00395400 (-63.9%)
500     200     0,01472000         0,00712300 (-51.6%)
2500    40      0,03809000         0,02147700 (-43.6%)
8000    12      0,09957100         0,06202100 (-37.7%)

vnegd:
rept    loop    master             patch
8       12500   0,00594600         0,00543800 (-8.5%)
25      4000    0,00575200         0,00396400 (-31.1%)
100     1000    0,00676100         0,00394800 (-41.6%)
500     200     0,01149300         0,00709400 (-38.3%)
2500    40      0,03441500         0,02169600 (-37.0%)
8000    12      0,09516900         0,06337000 (-33.4%)

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20221019125040.48028-5-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index f7047ed2aacc12bf137762456ba5b5f1033512e4..b2e910b0899f16c1f779632dd382c18c0e69b349 100644 (file)
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -229,8 +229,6 @@ DEF_HELPER_FLAGS_2(VSTRIBL, TCG_CALL_NO_RWG, i32, avr, avr)
 DEF_HELPER_FLAGS_2(VSTRIBR, TCG_CALL_NO_RWG, i32, avr, avr)
 DEF_HELPER_FLAGS_2(VSTRIHL, TCG_CALL_NO_RWG, i32, avr, avr)
 DEF_HELPER_FLAGS_2(VSTRIHR, TCG_CALL_NO_RWG, i32, avr, avr)
-DEF_HELPER_FLAGS_2(vnegw, TCG_CALL_NO_RWG, void, avr, avr)
-DEF_HELPER_FLAGS_2(vnegd, TCG_CALL_NO_RWG, void, avr, avr)
 DEF_HELPER_FLAGS_2(vupkhpx, TCG_CALL_NO_RWG, void, avr, avr)
 DEF_HELPER_FLAGS_2(vupklpx, TCG_CALL_NO_RWG, void, avr, avr)
 DEF_HELPER_FLAGS_2(vupkhsb, TCG_CALL_NO_RWG, void, avr, avr)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index c985f8f1bfced1f480e89cd2ec58b844e19101b1..2fafde075b09d4c374c64e1a604e959d21acae39 100644 (file)
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -629,6 +629,9 @@ VEXTSH2D        000100 ..... 11001 ..... 11000000010    @VX_tb
 VEXTSW2D        000100 ..... 11010 ..... 11000000010    @VX_tb
 VEXTSD2Q        000100 ..... 11011 ..... 11000000010    @VX_tb
 
+VNEGD           000100 ..... 00111 ..... 11000000010    @VX_tb
+VNEGW           000100 ..... 00110 ..... 11000000010    @VX_tb
+
 ## Vector Mask Manipulation Instructions
 
 MTVSRBM         000100 ..... 10000 ..... 11001000010    @VX_tb

diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index f8dd12e8ae3181691e489f7b711ba0c9fd702625..c7fd0d1faa4178b948e5daf6e1bd2749d1e8306c 100644 (file)
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1928,18 +1928,6 @@ XXBLEND(W, 32)
 XXBLEND(D, 64)
 #undef XXBLEND
 
-#define VNEG(name, element)                                         \
-void helper_##name(ppc_avr_t *r, ppc_avr_t *b)                      \
-{                                                                   \
-    int i;                                                          \
-    for (i = 0; i < ARRAY_SIZE(r->element); i++) {                  \
-        r->element[i] = -b->element[i];                             \
-    }                                                               \
-}
-VNEG(vnegw, s32)
-VNEG(vnegd, s64)
-#undef VNEG
-
 void helper_vsro(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
 {
     int sh = (b->VsrB(0xf) >> 3) & 0xf;

diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index f52485a5f1e6b3ddb3dd489a84bbb3f0eb147f9e..b9a9e83ab34c4aadd39b952204755b1a520e2a9d 100644 (file)
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -2625,8 +2625,19 @@ GEN_VXFORM_NOA(vclzb, 1, 28)
 GEN_VXFORM_NOA(vclzh, 1, 29)
 GEN_VXFORM_TRANS(vclzw, 1, 30)
 GEN_VXFORM_TRANS(vclzd, 1, 31)
-GEN_VXFORM_NOA_2(vnegw, 1, 24, 6)
-GEN_VXFORM_NOA_2(vnegd, 1, 24, 7)
+
+static bool do_vneg(DisasContext *ctx, arg_VX_tb *a, unsigned vece)
+{
+    REQUIRE_INSNS_FLAGS2(ctx, ISA300);
+    REQUIRE_VECTOR(ctx);
+
+    tcg_gen_gvec_neg(vece, avr_full_offset(a->vrt), avr_full_offset(a->vrb),
+                     16, 16);
+    return true;
+}
+
+TRANS(VNEGW, do_vneg, MO_32)
+TRANS(VNEGD, do_vneg, MO_64)
 
 static void gen_vexts_i64(TCGv_i64 t, TCGv_i64 b, int64_t s)
 {

diff --git a/target/ppc/translate/vmx-ops.c.inc b/target/ppc/translate/vmx-ops.c.inc
index ded0234123e7f8e6637427026991fe9688c77df5..27908533ddc1a4d327b1a2539340de1ffe44aff2 100644 (file)
--- a/target/ppc/translate/vmx-ops.c.inc
+++ b/target/ppc/translate/vmx-ops.c.inc
@@ -181,8 +181,6 @@ GEN_VXFORM_300_EXT(vextractd, 6, 11, 0x100000),
 GEN_VXFORM(vspltisb, 6, 12),
 GEN_VXFORM(vspltish, 6, 13),
 GEN_VXFORM(vspltisw, 6, 14),
-GEN_VXFORM_300_EO(vnegw, 0x01, 0x18, 0x06),
-GEN_VXFORM_300_EO(vnegd, 0x01, 0x18, 0x07),
 GEN_VXFORM_300_EO(vctzb, 0x01, 0x18, 0x1C),
 GEN_VXFORM_300_EO(vctzh, 0x01, 0x18, 0x1D),
 GEN_VXFORM_300_EO(vctzw, 0x01, 0x18, 0x1E),