target/ppc: Move VMH[R]ADDSHS instruction to decodetree

This patch moves VMHADDSHS and VMHRADDSHS to decodetree I couldn't find
a satisfactory implementation with TCG inline.

vmhaddshs:
rept    loop    master             patch
8       12500   0,02983400         0,02648500 (-11.2%)
25      4000    0,02946000         0,02518000 (-14.5%)
100     1000    0,03104300         0,02638000 (-15.0%)
500     200     0,04002000         0,03502500 (-12.5%)
2500    40      0,08090100         0,07562200 (-6.5%)
8000    12      0,19242600         0,18626800 (-3.2%)

vmhraddshs:
rept    loop    master             patch
8       12500   0,03078600         0,02851000 (-7.4%)
25      4000    0,02793200         0,02746900 (-1.7%)
100     1000    0,02886000         0,02839900 (-1.6%)
500     200     0,03714700         0,03799200 (+2.3%)
2500    40      0,07948000         0,07852200 (-1.2%)
8000    12      0,19049800         0,18813900 (-1.2%)

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20221019125040.48028-3-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 9c562ab00e42e17a1f80171e6c4525d22cfd92be..f02a9497b71476c75a74458ca4709cf124579412 100644 (file)
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -258,8 +258,8 @@ DEF_HELPER_4(vpkuhum, void, env, avr, avr, avr)
 DEF_HELPER_4(vpkuwum, void, env, avr, avr, avr)
 DEF_HELPER_4(vpkudum, void, env, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vpkpx, TCG_CALL_NO_RWG, void, avr, avr, avr)
-DEF_HELPER_5(vmhaddshs, void, env, avr, avr, avr, avr)
-DEF_HELPER_5(vmhraddshs, void, env, avr, avr, avr, avr)
+DEF_HELPER_5(VMHADDSHS, void, env, avr, avr, avr, avr)
+DEF_HELPER_5(VMHRADDSHS, void, env, avr, avr, avr, avr)
 DEF_HELPER_FLAGS_4(VMSUMUHM, TCG_CALL_NO_RWG, void, avr, avr, avr, avr)
 DEF_HELPER_5(VMSUMUHS, void, env, avr, avr, avr, avr)
 DEF_HELPER_FLAGS_4(VMSUMSHM, TCG_CALL_NO_RWG, void, avr, avr, avr, avr)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 9ba1689230cc512e1acb6b7adfc72e6eedfa04e0..4e142d5e23315fdddb9fe2dd97796e7c80076145 100644 (file)
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -694,6 +694,8 @@ VMSUMCUD        000100 ..... ..... ..... ..... 010111   @VA
 VMSUMUDM        000100 ..... ..... ..... ..... 100011   @VA
 
 VMLADDUHM       000100 ..... ..... ..... ..... 100010   @VA
+VMHADDSHS       000100 ..... ..... ..... ..... 100000   @VA
+VMHRADDSHS      000100 ..... ..... ..... ..... 100001   @VA
 
 ## Vector String Instructions
 

diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 0d25000b2a3e568c7fd605f57822a3672902269d..ae1ba8084d27983a622015451c90fff8ccc1c62c 100644 (file)
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -939,7 +939,7 @@ target_ulong helper_vctzlsbb(ppc_avr_t *r)
     return count;
 }
 
-void helper_vmhaddshs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
+void helper_VMHADDSHS(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
                       ppc_avr_t *b, ppc_avr_t *c)
 {
     int sat = 0;
@@ -957,7 +957,7 @@ void helper_vmhaddshs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
     }
 }
 
-void helper_vmhraddshs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
+void helper_VMHRADDSHS(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
                        ppc_avr_t *b, ppc_avr_t *c)
 {
     int sat = 0;

diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 9f18c6d4f28c76a2d83d87158563e58cf50df96a..3acd585a2f87ef6c8626305568a13aa14e8a05fd 100644 (file)
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -2521,7 +2521,7 @@ static void glue(gen_, name0##_##name1)(DisasContext *ctx)              \
         tcg_temp_free_ptr(rd);                                          \
     }
 
-GEN_VAFORM_PAIRED(vmhaddshs, vmhraddshs, 16)
+GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23)
 
 static bool do_va_helper(DisasContext *ctx, arg_VA *a,
     void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr))
@@ -2620,7 +2620,8 @@ static bool do_va_env_helper(DisasContext *ctx, arg_VA *a,
 TRANS_FLAGS(ALTIVEC, VMSUMUHS, do_va_env_helper, gen_helper_VMSUMUHS)
 TRANS_FLAGS(ALTIVEC, VMSUMSHS, do_va_env_helper, gen_helper_VMSUMSHS)
 
-GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23)
+TRANS_FLAGS(ALTIVEC, VMHADDSHS, do_va_env_helper, gen_helper_VMHADDSHS)
+TRANS_FLAGS(ALTIVEC, VMHRADDSHS, do_va_env_helper, gen_helper_VMHRADDSHS)
 
 GEN_VXFORM_NOA(vclzb, 1, 28)
 GEN_VXFORM_NOA(vclzh, 1, 29)

diff --git a/target/ppc/translate/vmx-ops.c.inc b/target/ppc/translate/vmx-ops.c.inc
index a3a0fd0650054a1936ea1b4faeb4c4aaa8824890..7cd9d40e0626491ddb8bf703bfc0b88eb4e96646 100644 (file)
--- a/target/ppc/translate/vmx-ops.c.inc
+++ b/target/ppc/translate/vmx-ops.c.inc
@@ -219,7 +219,6 @@ GEN_VXFORM_UIMM(vctsxs, 5, 15),
 
 #define GEN_VAFORM_PAIRED(name0, name1, opc2)                           \
     GEN_HANDLER(name0##_##name1, 0x04, opc2, 0xFF, 0x00000000, PPC_ALTIVEC)
-GEN_VAFORM_PAIRED(vmhaddshs, vmhraddshs, 16),
 GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23),
 
 GEN_VXFORM_DUAL(vclzb, vpopcntb, 1, 28, PPC_NONE, PPC2_ALTIVEC_207),