Re: [Qemu-devel] [PATCH v3 1/8] target/ppc: Optimize emulation of lvsl and lvsr instructions

2019-06-26 Thread Richard Henderson
On 6/21/19 1:07 PM, Stefan Brankovic wrote:
> +#if defined(TARGET_PPC64)
> +tcg_gen_andi_i64(sh, EA, 0xfULL);
> +#else
> +tcg_gen_ext_i32_i64(sh, EA);
> +tcg_gen_andi_i64(sh, sh, 0xfULL);
> +#endif

Didn't see v3 before reviewing v2, however as noted there, tcg_gen_extu_tl_i64.


r~



[Qemu-devel] [PATCH v3 1/8] target/ppc: Optimize emulation of lvsl and lvsr instructions

2019-06-21 Thread Stefan Brankovic
Adding simple macro that is calling tcg implementation of appropriate
instruction if altivec support is active.

Optimization of altivec instruction lvsl (Load Vector for Shift Left).
Place bytes sh:sh+15 of value 0x00 || 0x01 || 0x02 || ... || 0x1E || 0x1F
in destination register. Sh is calculated by adding 2 source registers and
getting bits 60-63 of result.

First, the bits [28-31] are placed from EA to variable sh. After that,
the bytes are created in the following way:
sh:(sh+7) of X(from description) by multiplying sh with 0x0101010101010101
followed by addition of the result with 0x0001020304050607. Value obtained
is placed in higher doubleword element of vD.
(sh+8):(sh+15) by adding the result of previous multiplication with
0x08090a0b0c0d0e0f. Value obtained is placed in lower doubleword element
of vD.

Optimization of altivec instruction lvsr (Load Vector for Shift Right).
Place bytes 16-sh:31-sh of value 0x00 || 0x01 || 0x02 || ... || 0x1E ||
0x1F in destination register. Sh is calculated by adding 2 source
registers and getting bits 60-63 of result.

First, the bits [28-31] are placed from EA to variable sh. After that,
the bytes are created in the following way:
sh:(sh+7) of X(from description) by multiplying sh with 0x0101010101010101
followed by substraction of the result from 0x1011121314151617. Value
obtained is placed in higher doubleword element of vD.
(sh+8):(sh+15) by substracting the result of previous multiplication from
0x18191a1b1c1d1e1f. Value obtained is placed in lower doubleword element
of vD.

Signed-off-by: Stefan Brankovic 
---
 target/ppc/helper.h |   2 -
 target/ppc/int_helper.c |  18 -
 target/ppc/translate/vmx-impl.inc.c | 129 +++-
 3 files changed, 97 insertions(+), 52 deletions(-)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 02b67a3..c82105e 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -189,8 +189,6 @@ DEF_HELPER_2(vprtybw, void, avr, avr)
 DEF_HELPER_2(vprtybd, void, avr, avr)
 DEF_HELPER_2(vprtybq, void, avr, avr)
 DEF_HELPER_3(vsubcuw, void, avr, avr, avr)
-DEF_HELPER_2(lvsl, void, avr, tl)
-DEF_HELPER_2(lvsr, void, avr, tl)
 DEF_HELPER_FLAGS_5(vaddsbs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
 DEF_HELPER_FLAGS_5(vaddshs, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
 DEF_HELPER_FLAGS_5(vaddsws, TCG_CALL_NO_RWG, void, avr, avr, avr, avr, i32)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 8ce89f2..9505f4c 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -457,24 +457,6 @@ SATCVT(sd, uw, int64_t, uint32_t, 0, UINT32_MAX)
 #undef SATCVT
 #undef SATCVTU
 
-void helper_lvsl(ppc_avr_t *r, target_ulong sh)
-{
-int i, j = (sh & 0xf);
-
-for (i = 0; i < ARRAY_SIZE(r->u8); i++) {
-r->VsrB(i) = j++;
-}
-}
-
-void helper_lvsr(ppc_avr_t *r, target_ulong sh)
-{
-int i, j = 0x10 - (sh & 0xf);
-
-for (i = 0; i < ARRAY_SIZE(r->u8); i++) {
-r->VsrB(i) = j++;
-}
-}
-
 void helper_mtvscr(CPUPPCState *env, uint32_t vscr)
 {
 env->vscr = vscr & ~(1u << VSCR_SAT);
diff --git a/target/ppc/translate/vmx-impl.inc.c 
b/target/ppc/translate/vmx-impl.inc.c
index 663275b..eba6355 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -142,38 +142,6 @@ GEN_VR_STVE(bx, 0x07, 0x04, 1);
 GEN_VR_STVE(hx, 0x07, 0x05, 2);
 GEN_VR_STVE(wx, 0x07, 0x06, 4);
 
-static void gen_lvsl(DisasContext *ctx)
-{
-TCGv_ptr rd;
-TCGv EA;
-if (unlikely(!ctx->altivec_enabled)) {
-gen_exception(ctx, POWERPC_EXCP_VPU);
-return;
-}
-EA = tcg_temp_new();
-gen_addr_reg_index(ctx, EA);
-rd = gen_avr_ptr(rD(ctx->opcode));
-gen_helper_lvsl(rd, EA);
-tcg_temp_free(EA);
-tcg_temp_free_ptr(rd);
-}
-
-static void gen_lvsr(DisasContext *ctx)
-{
-TCGv_ptr rd;
-TCGv EA;
-if (unlikely(!ctx->altivec_enabled)) {
-gen_exception(ctx, POWERPC_EXCP_VPU);
-return;
-}
-EA = tcg_temp_new();
-gen_addr_reg_index(ctx, EA);
-rd = gen_avr_ptr(rD(ctx->opcode));
-gen_helper_lvsr(rd, EA);
-tcg_temp_free(EA);
-tcg_temp_free_ptr(rd);
-}
-
 static void gen_mfvscr(DisasContext *ctx)
 {
 TCGv_i32 t;
@@ -316,6 +284,16 @@ static void glue(gen_, name)(DisasContext *ctx)
 \
 tcg_temp_free_ptr(rd);  \
 }
 
+#define GEN_VXFORM_TRANS(name, opc2, opc3)  \
+static void glue(gen_, name)(DisasContext *ctx) \
+{   \
+if (unlikely(!ctx->altivec_enabled)) {  \
+gen_exception(ctx, POWERPC_EXCP_VPU);   \
+return; \
+}   \
+trans_##name(ctx);