All of lore.kernel.org
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: david@redhat.com
Subject: [Qemu-devel] [PATCH 31/38] target/ppc: Use vector variable shifts for VS{L, R, RA}{B, H, W, D}
Date: Fri, 19 Apr 2019 21:34:35 -1000	[thread overview]
Message-ID: <20190420073442.7488-32-richard.henderson@linaro.org> (raw)
In-Reply-To: <20190420073442.7488-1-richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/helper.h                 |  24 ++--
 target/ppc/int_helper.c             |   6 +-
 target/ppc/translate/vmx-impl.inc.c | 168 ++++++++++++++++++++++++++--
 3 files changed, 172 insertions(+), 26 deletions(-)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 638a6e99c4..5416dc55ce 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -180,18 +180,18 @@ DEF_HELPER_3(vmuloub, void, avr, avr, avr)
 DEF_HELPER_3(vmulouh, void, avr, avr, avr)
 DEF_HELPER_3(vmulouw, void, avr, avr, avr)
 DEF_HELPER_3(vmuluwm, void, avr, avr, avr)
-DEF_HELPER_3(vsrab, void, avr, avr, avr)
-DEF_HELPER_3(vsrah, void, avr, avr, avr)
-DEF_HELPER_3(vsraw, void, avr, avr, avr)
-DEF_HELPER_3(vsrad, void, avr, avr, avr)
-DEF_HELPER_3(vsrb, void, avr, avr, avr)
-DEF_HELPER_3(vsrh, void, avr, avr, avr)
-DEF_HELPER_3(vsrw, void, avr, avr, avr)
-DEF_HELPER_3(vsrd, void, avr, avr, avr)
-DEF_HELPER_3(vslb, void, avr, avr, avr)
-DEF_HELPER_3(vslh, void, avr, avr, avr)
-DEF_HELPER_3(vslw, void, avr, avr, avr)
-DEF_HELPER_3(vsld, void, avr, avr, avr)
+DEF_HELPER_4(vsrab, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsrah, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsraw, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsrad, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsrb, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsrh, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsrw, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsrd, void, avr, avr, avr, i32)
+DEF_HELPER_4(vslb, void, avr, avr, avr, i32)
+DEF_HELPER_4(vslh, void, avr, avr, avr, i32)
+DEF_HELPER_4(vslw, void, avr, avr, avr, i32)
+DEF_HELPER_4(vsld, void, avr, avr, avr, i32)
 DEF_HELPER_3(vslo, void, avr, avr, avr)
 DEF_HELPER_3(vsro, void, avr, avr, avr)
 DEF_HELPER_3(vsrv, void, avr, avr, avr)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 162add561e..35ec1ccdfb 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1770,7 +1770,8 @@ VSHIFT(r, 0)
 #undef VSHIFT
 
 #define VSL(suffix, element, mask)                                      \
-    void helper_vsl##suffix(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)   \
+    void helper_vsl##suffix(ppc_avr_t *r, ppc_avr_t *a,                 \
+                            ppc_avr_t *b, uint32_t desc)                \
     {                                                                   \
         int i;                                                          \
                                                                         \
@@ -1958,7 +1959,8 @@ VNEG(vnegd, s64)
 #undef VNEG
 
 #define VSR(suffix, element, mask)                                      \
-    void helper_vsr##suffix(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)   \
+    void helper_vsr##suffix(ppc_avr_t *r, ppc_avr_t *a,                 \
+                            ppc_avr_t *b, uint32_t desc)                \
     {                                                                   \
         int i;                                                          \
                                                                         \
diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c
index c83e605a00..8cc2e99963 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -511,6 +511,150 @@ static void gen_vmrgow(DisasContext *ctx)
     tcg_temp_free_i64(avr);
 }
 
+static void gen_vsl_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(b);
+    tcg_gen_dupi_vec(vece, t, (8 << vece) - 1);
+    tcg_gen_and_vec(vece, b, b, t);
+    tcg_temp_free_vec(t);
+    tcg_gen_shlv_vec(vece, d, a, b);
+}
+
+static void gen_vslw_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    tcg_gen_andi_i32(b, b, 31);
+    tcg_gen_shl_i32(d, a, b);
+}
+
+static void gen_vsld_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+    tcg_gen_andi_i64(b, b, 63);
+    tcg_gen_shl_i64(d, a, b);
+}
+
+static void gen__vsl(unsigned vece, uint32_t dofs, uint32_t aofs,
+                     uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode shlv_list[] = { INDEX_op_shlv_vec, 0 };
+    static const GVecGen3 g[4] = {
+        { .fniv = gen_vsl_vec,
+          .fno = gen_helper_vslb,
+          .opt_opc = shlv_list,
+          .vece = MO_8 },
+        { .fniv = gen_vsl_vec,
+          .fno = gen_helper_vslh,
+          .opt_opc = shlv_list,
+          .vece = MO_16 },
+        { .fni4 = gen_vslw_i32,
+          .fniv = gen_vsl_vec,
+          .fno = gen_helper_vslw,
+          .opt_opc = shlv_list,
+          .vece = MO_32 },
+        { .fni8 = gen_vsld_i64,
+          .fniv = gen_vsl_vec,
+          .fno = gen_helper_vsld,
+          .opt_opc = shlv_list,
+          .vece = MO_64 }
+    };
+    tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
+}
+
+static void gen_vsr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(b);
+    tcg_gen_dupi_vec(vece, t, (8 << vece) - 1);
+    tcg_gen_and_vec(vece, b, b, t);
+    tcg_temp_free_vec(t);
+    tcg_gen_shrv_vec(vece, d, a, b);
+}
+
+static void gen_vsrw_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    tcg_gen_andi_i32(b, b, 31);
+    tcg_gen_shr_i32(d, a, b);
+}
+
+static void gen_vsrd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+    tcg_gen_andi_i64(b, b, 63);
+    tcg_gen_shr_i64(d, a, b);
+}
+
+static void gen__vsr(unsigned vece, uint32_t dofs, uint32_t aofs,
+                     uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode shrv_list[] = { INDEX_op_shrv_vec, 0 };
+    static const GVecGen3 g[4] = {
+        { .fniv = gen_vsr_vec,
+          .fno = gen_helper_vsrb,
+          .opt_opc = shrv_list,
+          .vece = MO_8 },
+        { .fniv = gen_vsr_vec,
+          .fno = gen_helper_vsrh,
+          .opt_opc = shrv_list,
+          .vece = MO_16 },
+        { .fni4 = gen_vsrw_i32,
+          .fniv = gen_vsr_vec,
+          .fno = gen_helper_vsrw,
+          .opt_opc = shrv_list,
+          .vece = MO_32 },
+        { .fni8 = gen_vsrd_i64,
+          .fniv = gen_vsr_vec,
+          .fno = gen_helper_vsrd,
+          .opt_opc = shrv_list,
+          .vece = MO_64 }
+    };
+    tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
+}
+
+static void gen_vsra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b)
+{
+    TCGv_vec t = tcg_temp_new_vec_matching(b);
+    tcg_gen_dupi_vec(vece, t, (8 << vece) - 1);
+    tcg_gen_and_vec(vece, b, b, t);
+    tcg_temp_free_vec(t);
+    tcg_gen_sarv_vec(vece, d, a, b);
+}
+
+static void gen_vsraw_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    tcg_gen_andi_i32(b, b, 31);
+    tcg_gen_sar_i32(d, a, b);
+}
+
+static void gen_vsrad_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+    tcg_gen_andi_i64(b, b, 63);
+    tcg_gen_sar_i64(d, a, b);
+}
+
+static void gen__vsra(unsigned vece, uint32_t dofs, uint32_t aofs,
+                      uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const TCGOpcode sarv_list[] = { INDEX_op_sarv_vec, 0 };
+    static const GVecGen3 g[4] = {
+        { .fniv = gen_vsra_vec,
+          .fno = gen_helper_vsrab,
+          .opt_opc = sarv_list,
+          .vece = MO_8 },
+        { .fniv = gen_vsra_vec,
+          .fno = gen_helper_vsrah,
+          .opt_opc = sarv_list,
+          .vece = MO_16 },
+        { .fni4 = gen_vsraw_i32,
+          .fniv = gen_vsra_vec,
+          .fno = gen_helper_vsraw,
+          .opt_opc = sarv_list,
+          .vece = MO_32 },
+        { .fni8 = gen_vsrad_i64,
+          .fniv = gen_vsra_vec,
+          .fno = gen_helper_vsrad,
+          .opt_opc = sarv_list,
+          .vece = MO_64 }
+    };
+    tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
+}
+
 GEN_VXFORM(vmuloub, 4, 0);
 GEN_VXFORM(vmulouh, 4, 1);
 GEN_VXFORM(vmulouw, 4, 2);
@@ -526,21 +670,21 @@ GEN_VXFORM(vmuleuw, 4, 10);
 GEN_VXFORM(vmulesb, 4, 12);
 GEN_VXFORM(vmulesh, 4, 13);
 GEN_VXFORM(vmulesw, 4, 14);
-GEN_VXFORM(vslb, 2, 4);
-GEN_VXFORM(vslh, 2, 5);
-GEN_VXFORM(vslw, 2, 6);
+GEN_VXFORM_V(vslb, MO_8, gen__vsl, 2, 4);
+GEN_VXFORM_V(vslh, MO_16, gen__vsl, 2, 5);
+GEN_VXFORM_V(vslw, MO_32, gen__vsl, 2, 6);
+GEN_VXFORM_V(vsld, MO_64, gen__vsl, 2, 23);
 GEN_VXFORM(vrlwnm, 2, 6);
 GEN_VXFORM_DUAL(vslw, PPC_ALTIVEC, PPC_NONE, \
                 vrlwnm, PPC_NONE, PPC2_ISA300)
-GEN_VXFORM(vsld, 2, 23);
-GEN_VXFORM(vsrb, 2, 8);
-GEN_VXFORM(vsrh, 2, 9);
-GEN_VXFORM(vsrw, 2, 10);
-GEN_VXFORM(vsrd, 2, 27);
-GEN_VXFORM(vsrab, 2, 12);
-GEN_VXFORM(vsrah, 2, 13);
-GEN_VXFORM(vsraw, 2, 14);
-GEN_VXFORM(vsrad, 2, 15);
+GEN_VXFORM_V(vsrb, MO_8, gen__vsr, 2, 8);
+GEN_VXFORM_V(vsrh, MO_16, gen__vsr, 2, 9);
+GEN_VXFORM_V(vsrw, MO_32, gen__vsr, 2, 10);
+GEN_VXFORM_V(vsrd, MO_64, gen__vsr, 2, 27);
+GEN_VXFORM_V(vsrab, MO_8, gen__vsra, 2, 12);
+GEN_VXFORM_V(vsrah, MO_16, gen__vsra, 2, 13);
+GEN_VXFORM_V(vsraw, MO_32, gen__vsra, 2, 14);
+GEN_VXFORM_V(vsrad, MO_64, gen__vsra, 2, 15);
 GEN_VXFORM(vsrv, 2, 28);
 GEN_VXFORM(vslv, 2, 29);
 GEN_VXFORM(vslo, 6, 16);
-- 
2.17.1

  parent reply	other threads:[~2019-04-20  7:35 UTC|newest]

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-20  7:34 [Qemu-devel] [PATCH 00/38] tcg vector improvements Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 01/38] target/arm: Fill in .opc for cmtst_op Richard Henderson
2019-04-23  8:00   ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 02/38] tcg: Assert fixed_reg is read-only Richard Henderson
2019-04-23  8:03   ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 03/38] tcg: Return bool success from tcg_out_mov Richard Henderson
2019-04-20 10:56   ` Philippe Mathieu-Daudé
2019-04-23  8:27   ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 04/38] tcg: Support cross-class moves without instruction support Richard Henderson
2019-04-23  8:29   ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 05/38] tcg: Allow add_vec, sub_vec, neg_vec, not_vec to be expanded Richard Henderson
2019-04-23  8:33   ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 06/38] tcg: Promote tcg_out_{dup, dupi}_vec to backend interface Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 07/38] tcg: Manually expand INDEX_op_dup_vec Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 08/38] tcg: Add tcg_out_dupm_vec to the backend interface Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 09/38] tcg/i386: Implement tcg_out_dupm_vec Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 10/38] tcg/aarch64: " Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 11/38] tcg: Add INDEX_op_dup_mem_vec Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 12/38] tcg: Add gvec expanders for variable shift Richard Henderson
2019-04-23 19:04   ` David Hildenbrand
2019-04-23 19:28     ` Richard Henderson
2019-04-23 21:02       ` David Hildenbrand
2019-04-23 21:40         ` Richard Henderson
2019-04-23 21:57           ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 13/38] tcg/i386: Support vector variable shift opcodes Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 14/38] tcg/aarch64: " Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 15/38] tcg: Implement tcg_gen_gvec_3i() Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 16/38] tcg: Specify optional vector requirements with a list Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 17/38] tcg: Add gvec expanders for vector shift by scalar Richard Henderson
2019-04-23 18:58   ` David Hildenbrand
2019-04-23 19:21     ` Richard Henderson
2019-04-23 21:05       ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 18/38] tcg/i386: Support vector scalar shift opcodes Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 19/38] tcg: Add support for integer absolute value Richard Henderson
2019-04-23  8:52   ` Philippe Mathieu-Daudé
2019-04-23 18:37   ` David Hildenbrand
2019-04-23 22:09     ` Philippe Mathieu-Daudé
2019-04-23 22:29       ` Richard Henderson
2019-04-23 23:05         ` Philippe Mathieu-Daudé
2019-04-20  7:34 ` [Qemu-devel] [PATCH 20/38] tcg: Add support for vector " Richard Henderson
2019-04-23 18:35   ` David Hildenbrand
2019-04-20  7:34 ` [Qemu-devel] [PATCH 21/38] target/arm: Use tcg_gen_abs_i64 and tcg_gen_gvec_abs Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 22/38] target/cris: Use tcg_gen_abs_tl Richard Henderson
2019-04-23 10:09   ` Philippe Mathieu-Daudé
2019-04-20  7:34 ` [Qemu-devel] [PATCH 23/38] target/ppc: " Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 24/38] target/s390x: Use tcg_gen_abs_i64 Richard Henderson
2019-04-23 18:40   ` David Hildenbrand
2019-04-23 22:12   ` Philippe Mathieu-Daudé
2019-04-20  7:34 ` [Qemu-devel] [PATCH 25/38] target/xtensa: Use tcg_gen_abs_i32 Richard Henderson
2019-04-23 22:14   ` Philippe Mathieu-Daudé
2019-04-20  7:34 ` [Qemu-devel] [PATCH 26/38] tcg/i386: Support vector absolute value Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 27/38] tcg/aarch64: " Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 28/38] tcg: Add support for vector comparison select Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 29/38] tcg/i386: Support vector comparison select value Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 30/38] tcg/aarch64: " Richard Henderson
2019-04-20  7:34 ` Richard Henderson [this message]
2019-04-20  7:34 ` [Qemu-devel] [PATCH 32/38] target/arm: Vectorize USHL and SSHL Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 33/38] tcg/aarch64: Do not advertise minmax for MO_64 Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 34/38] tcg: Do not recreate INDEX_op_neg_vec unless supported Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 35/38] tcg: Introduce do_op3_nofail for vector expansion Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 36/38] tcg: Expand vector minmax using cmp+cmpsel Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 37/38] tcg/aarch64: Use MVNI for expansion of dupi Richard Henderson
2019-04-20  7:34 ` [Qemu-devel] [PATCH 38/38] tcg/aarch64: Use ORRI and BICI for vector logical operations Richard Henderson
2019-04-20  8:09 ` [Qemu-devel] [PATCH 00/38] tcg vector improvements no-reply
2019-04-23 19:15 ` David Hildenbrand
2019-04-23 20:26   ` Richard Henderson
2019-04-23 20:31     ` David Hildenbrand
2019-04-29 19:28 ` David Hildenbrand
2019-04-29 20:19   ` Richard Henderson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190420073442.7488-32-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=david@redhat.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.