From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: peter.maydell@linaro.org, "Philippe Mathieu-Daudé" <philmd@redhat.com>
Subject: [PULL 4/5] tcg: Tidy tcg-runtime-gvec.c DUP*
Date: Tue, 17 Mar 2020 12:00:12 -0700 [thread overview]
Message-ID: <20200317190013.25036-5-richard.henderson@linaro.org> (raw)
In-Reply-To: <20200317190013.25036-1-richard.henderson@linaro.org>
Partial cleanup from the CONFIG_VECTOR16 removal.
Replace the DUP* expansions with the scalar argument.
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
accel/tcg/tcg-runtime-gvec.c | 50 +++++++++++-------------------------
1 file changed, 15 insertions(+), 35 deletions(-)
diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c
index 97852b515b..f2199f14b4 100644
--- a/accel/tcg/tcg-runtime-gvec.c
+++ b/accel/tcg/tcg-runtime-gvec.c
@@ -24,11 +24,6 @@
#include "tcg/tcg-gvec-desc.h"
-#define DUP16(X) X
-#define DUP8(X) X
-#define DUP4(X) X
-#define DUP2(X) X
-
static inline void clear_high(void *d, intptr_t oprsz, uint32_t desc)
{
intptr_t maxsz = simd_maxsz(desc);
@@ -88,11 +83,10 @@ void HELPER(gvec_add64)(void *d, void *a, void *b, uint32_t desc)
void HELPER(gvec_adds8)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint8_t vecb = (uint8_t)DUP16(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
- *(uint8_t *)(d + i) = *(uint8_t *)(a + i) + vecb;
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) + (uint8_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -100,11 +94,10 @@ void HELPER(gvec_adds8)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_adds16)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint16_t vecb = (uint16_t)DUP8(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
- *(uint16_t *)(d + i) = *(uint16_t *)(a + i) + vecb;
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) + (uint16_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -112,11 +105,10 @@ void HELPER(gvec_adds16)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_adds32)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint32_t vecb = (uint32_t)DUP4(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
- *(uint32_t *)(d + i) = *(uint32_t *)(a + i) + vecb;
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) + (uint32_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -124,11 +116,10 @@ void HELPER(gvec_adds32)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_adds64)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
- *(uint64_t *)(d + i) = *(uint64_t *)(a + i) + vecb;
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) + b;
}
clear_high(d, oprsz, desc);
}
@@ -180,11 +171,10 @@ void HELPER(gvec_sub64)(void *d, void *a, void *b, uint32_t desc)
void HELPER(gvec_subs8)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint8_t vecb = (uint8_t)DUP16(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
- *(uint8_t *)(d + i) = *(uint8_t *)(a + i) - vecb;
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) - (uint8_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -192,11 +182,10 @@ void HELPER(gvec_subs8)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_subs16)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint16_t vecb = (uint16_t)DUP8(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
- *(uint16_t *)(d + i) = *(uint16_t *)(a + i) - vecb;
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) - (uint16_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -204,11 +193,10 @@ void HELPER(gvec_subs16)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_subs32)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint32_t vecb = (uint32_t)DUP4(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
- *(uint32_t *)(d + i) = *(uint32_t *)(a + i) - vecb;
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) - (uint32_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -216,11 +204,10 @@ void HELPER(gvec_subs32)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_subs64)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
- *(uint64_t *)(d + i) = *(uint64_t *)(a + i) - vecb;
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) - b;
}
clear_high(d, oprsz, desc);
}
@@ -272,11 +259,10 @@ void HELPER(gvec_mul64)(void *d, void *a, void *b, uint32_t desc)
void HELPER(gvec_muls8)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint8_t vecb = (uint8_t)DUP16(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
- *(uint8_t *)(d + i) = *(uint8_t *)(a + i) * vecb;
+ *(uint8_t *)(d + i) = *(uint8_t *)(a + i) * (uint8_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -284,11 +270,10 @@ void HELPER(gvec_muls8)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_muls16)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint16_t vecb = (uint16_t)DUP8(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
- *(uint16_t *)(d + i) = *(uint16_t *)(a + i) * vecb;
+ *(uint16_t *)(d + i) = *(uint16_t *)(a + i) * (uint16_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -296,11 +281,10 @@ void HELPER(gvec_muls16)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_muls32)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint32_t vecb = (uint32_t)DUP4(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
- *(uint32_t *)(d + i) = *(uint32_t *)(a + i) * vecb;
+ *(uint32_t *)(d + i) = *(uint32_t *)(a + i) * (uint32_t)b;
}
clear_high(d, oprsz, desc);
}
@@ -308,11 +292,10 @@ void HELPER(gvec_muls32)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_muls64)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
- *(uint64_t *)(d + i) = *(uint64_t *)(a + i) * vecb;
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) * b;
}
clear_high(d, oprsz, desc);
}
@@ -559,11 +542,10 @@ void HELPER(gvec_eqv)(void *d, void *a, void *b, uint32_t desc)
void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
- *(uint64_t *)(d + i) = *(uint64_t *)(a + i) & vecb;
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) & b;
}
clear_high(d, oprsz, desc);
}
@@ -571,11 +553,10 @@ void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
- *(uint64_t *)(d + i) = *(uint64_t *)(a + i) ^ vecb;
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) ^ b;
}
clear_high(d, oprsz, desc);
}
@@ -583,11 +564,10 @@ void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
void HELPER(gvec_ors)(void *d, void *a, uint64_t b, uint32_t desc)
{
intptr_t oprsz = simd_oprsz(desc);
- uint64_t vecb = (uint64_t)DUP2(b);
intptr_t i;
for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
- *(uint64_t *)(d + i) = *(uint64_t *)(a + i) | vecb;
+ *(uint64_t *)(d + i) = *(uint64_t *)(a + i) | b;
}
clear_high(d, oprsz, desc);
}
--
2.20.1
next prev parent reply other threads:[~2020-03-17 19:02 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-17 19:00 [PULL 0/5] tcg patch queue Richard Henderson
2020-03-17 19:00 ` [PULL 1/5] tcg/i386: Bound shift count expanding sari_vec Richard Henderson
2020-03-17 19:00 ` [PULL 2/5] tcg: Remove CONFIG_VECTOR16 Richard Henderson
2020-03-17 19:00 ` [PULL 3/5] tcg: Tidy tcg-runtime-gvec.c types Richard Henderson
2020-03-17 19:00 ` Richard Henderson [this message]
2020-03-17 19:00 ` [PULL 5/5] tcg: Remove tcg-runtime-gvec.c DO_CMP0 Richard Henderson
2020-03-17 23:34 ` [PULL 0/5] tcg patch queue no-reply
2020-03-19 10:17 ` Peter Maydell
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=20200317190013.25036-5-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=peter.maydell@linaro.org \
--cc=philmd@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 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).