From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: paul@nowt.org, richard.henderson@linaro.org
Subject: [PATCH v3 21/23] i386: Rewrite blendv helpers
Date: Thu, 1 Sep 2022 09:48:40 +0200 [thread overview]
Message-ID: <20220901074842.57424-22-pbonzini@redhat.com> (raw)
In-Reply-To: <20220901074842.57424-1-pbonzini@redhat.com>
From: Paul Brook <paul@nowt.org>
Rewrite the blendv helpers so that they can easily be extended to support
the AVX encodings, which make all 4 arguments explicit.
No functional changes to the existing helpers
Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-20-paul@nowt.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
target/i386/ops_sse.h | 86 ++++++++++++-------------------------------
1 file changed, 24 insertions(+), 62 deletions(-)
diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 7cfbcce49f..a11a0143bf 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -1591,76 +1591,38 @@ void glue(helper_palignr, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
}
}
-#define XMM0 (env->xmm_regs[0])
+#if SHIFT >= 1
-#if SHIFT == 1
#define SSE_HELPER_V(name, elem, num, F) \
- void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
+ void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) \
{ \
- d->elem(0) = F(d->elem(0), s->elem(0), XMM0.elem(0)); \
- d->elem(1) = F(d->elem(1), s->elem(1), XMM0.elem(1)); \
- if (num > 2) { \
- d->elem(2) = F(d->elem(2), s->elem(2), XMM0.elem(2)); \
- d->elem(3) = F(d->elem(3), s->elem(3), XMM0.elem(3)); \
- if (num > 4) { \
- d->elem(4) = F(d->elem(4), s->elem(4), XMM0.elem(4)); \
- d->elem(5) = F(d->elem(5), s->elem(5), XMM0.elem(5)); \
- d->elem(6) = F(d->elem(6), s->elem(6), XMM0.elem(6)); \
- d->elem(7) = F(d->elem(7), s->elem(7), XMM0.elem(7)); \
- if (num > 8) { \
- d->elem(8) = F(d->elem(8), s->elem(8), XMM0.elem(8)); \
- d->elem(9) = F(d->elem(9), s->elem(9), XMM0.elem(9)); \
- d->elem(10) = F(d->elem(10), s->elem(10), XMM0.elem(10)); \
- d->elem(11) = F(d->elem(11), s->elem(11), XMM0.elem(11)); \
- d->elem(12) = F(d->elem(12), s->elem(12), XMM0.elem(12)); \
- d->elem(13) = F(d->elem(13), s->elem(13), XMM0.elem(13)); \
- d->elem(14) = F(d->elem(14), s->elem(14), XMM0.elem(14)); \
- d->elem(15) = F(d->elem(15), s->elem(15), XMM0.elem(15)); \
- } \
- } \
+ Reg *v = d; \
+ Reg *m = &env->xmm_regs[0]; \
+ int i; \
+ for (i = 0; i < num; i++) { \
+ d->elem(i) = F(v->elem(i), s->elem(i), m->elem(i)); \
} \
}
#define SSE_HELPER_I(name, elem, num, F) \
- void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t imm) \
+ void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, \
+ uint32_t imm) \
{ \
- d->elem(0) = F(d->elem(0), s->elem(0), ((imm >> 0) & 1)); \
- d->elem(1) = F(d->elem(1), s->elem(1), ((imm >> 1) & 1)); \
- if (num > 2) { \
- d->elem(2) = F(d->elem(2), s->elem(2), ((imm >> 2) & 1)); \
- d->elem(3) = F(d->elem(3), s->elem(3), ((imm >> 3) & 1)); \
- if (num > 4) { \
- d->elem(4) = F(d->elem(4), s->elem(4), ((imm >> 4) & 1)); \
- d->elem(5) = F(d->elem(5), s->elem(5), ((imm >> 5) & 1)); \
- d->elem(6) = F(d->elem(6), s->elem(6), ((imm >> 6) & 1)); \
- d->elem(7) = F(d->elem(7), s->elem(7), ((imm >> 7) & 1)); \
- if (num > 8) { \
- d->elem(8) = F(d->elem(8), s->elem(8), ((imm >> 8) & 1)); \
- d->elem(9) = F(d->elem(9), s->elem(9), ((imm >> 9) & 1)); \
- d->elem(10) = F(d->elem(10), s->elem(10), \
- ((imm >> 10) & 1)); \
- d->elem(11) = F(d->elem(11), s->elem(11), \
- ((imm >> 11) & 1)); \
- d->elem(12) = F(d->elem(12), s->elem(12), \
- ((imm >> 12) & 1)); \
- d->elem(13) = F(d->elem(13), s->elem(13), \
- ((imm >> 13) & 1)); \
- d->elem(14) = F(d->elem(14), s->elem(14), \
- ((imm >> 14) & 1)); \
- d->elem(15) = F(d->elem(15), s->elem(15), \
- ((imm >> 15) & 1)); \
- } \
- } \
+ Reg *v = d; \
+ int i; \
+ for (i = 0; i < num; i++) { \
+ int j = i & 7; \
+ d->elem(i) = F(v->elem(i), s->elem(i), (imm >> j) & 1); \
} \
}
/* SSE4.1 op helpers */
-#define FBLENDVB(d, s, m) ((m & 0x80) ? s : d)
-#define FBLENDVPS(d, s, m) ((m & 0x80000000) ? s : d)
-#define FBLENDVPD(d, s, m) ((m & 0x8000000000000000LL) ? s : d)
-SSE_HELPER_V(helper_pblendvb, B, 16, FBLENDVB)
-SSE_HELPER_V(helper_blendvps, L, 4, FBLENDVPS)
-SSE_HELPER_V(helper_blendvpd, Q, 2, FBLENDVPD)
+#define FBLENDVB(v, s, m) ((m & 0x80) ? s : v)
+#define FBLENDVPS(v, s, m) ((m & 0x80000000) ? s : v)
+#define FBLENDVPD(v, s, m) ((m & 0x8000000000000000LL) ? s : v)
+SSE_HELPER_V(helper_pblendvb, B, 8 << SHIFT, FBLENDVB)
+SSE_HELPER_V(helper_blendvps, L, 2 << SHIFT, FBLENDVPS)
+SSE_HELPER_V(helper_blendvpd, Q, 1 << SHIFT, FBLENDVPD)
void glue(helper_ptest, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
{
@@ -1926,10 +1888,10 @@ void glue(helper_roundsd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
}
#endif
-#define FBLENDP(d, s, m) (m ? s : d)
-SSE_HELPER_I(helper_blendps, L, 4, FBLENDP)
-SSE_HELPER_I(helper_blendpd, Q, 2, FBLENDP)
-SSE_HELPER_I(helper_pblendw, W, 8, FBLENDP)
+#define FBLENDP(v, s, m) (m ? s : v)
+SSE_HELPER_I(helper_blendps, L, 2 << SHIFT, FBLENDP)
+SSE_HELPER_I(helper_blendpd, Q, 1 << SHIFT, FBLENDP)
+SSE_HELPER_I(helper_pblendw, W, 4 << SHIFT, FBLENDP)
void glue(helper_dpps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
uint32_t mask)
--
2.37.1
next prev parent reply other threads:[~2022-09-01 9:03 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-01 7:48 [PATCH v3 00/23] target/i386: make SSE helpers generic in the vector size Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 01/23] i386: do not use MOVL to move data between SSE registers Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 02/23] i386: formatting fixes Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 03/23] i386: Add ZMM_OFFSET macro Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 04/23] i386: Rework sse_op_table1 Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 05/23] i386: Rework sse_op_table6/7 Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 06/23] i386: Move 3DNOW decoder Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 07/23] i386: check SSE table flags instead of hardcoding opcodes Paolo Bonzini
2022-09-01 8:05 ` Richard Henderson
2022-09-01 7:48 ` [PATCH v3 08/23] i386: isolate MMX code more Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 09/23] i386: Add size suffix to vector FP helpers Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 10/23] i386: do not cast gen_helper_* function pointers Paolo Bonzini
2022-09-01 8:10 ` Richard Henderson
2022-09-01 7:48 ` [PATCH v3 11/23] i386: Add CHECK_NO_VEX Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 12/23] i386: Rewrite vector shift helper Paolo Bonzini
2022-09-01 8:11 ` Richard Henderson
2022-09-01 7:48 ` [PATCH v3 13/23] i386: Rewrite simple integer vector helpers Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 14/23] i386: Misc integer AVX helper prep Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 15/23] i386: Destructive vector helpers for AVX Paolo Bonzini
2022-09-01 8:16 ` Richard Henderson
2022-09-01 7:48 ` [PATCH v3 16/23] i386: Floating point arithmetic helper AVX prep Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 17/23] i386: reimplement AVX comparison helpers Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 18/23] i386: Dot product AVX helper prep Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 19/23] i386: Destructive FP helpers for AVX Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 20/23] i386: Misc AVX helper prep Paolo Bonzini
2022-09-01 7:48 ` Paolo Bonzini [this message]
2022-09-01 7:48 ` [PATCH v3 22/23] i386: AVX pclmulqdq prep Paolo Bonzini
2022-09-01 7:48 ` [PATCH v3 23/23] i386: AVX+AES helpers prep Paolo Bonzini
2022-09-01 8:19 ` 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=20220901074842.57424-22-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=paul@nowt.org \
--cc=qemu-devel@nongnu.org \
--cc=richard.henderson@linaro.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).