From: Christophe Lyon <christophe.lyon@st.com>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: "qemu-devel@nongnu.org" <qemu-devel@nongnu.org>
Subject: Re: [Qemu-devel] [PATCH] target-arm: Set the right overflow bit for neon 32 and 64 bit saturating add/sub.
Date: Mon, 24 Jan 2011 13:41:50 +0100 [thread overview]
Message-ID: <4D3D738E.5040709@st.com> (raw)
In-Reply-To: <AANLkTi=LOcx5=+3iTv+fhv09ceXTzfzrCVmT1qdXhxZs@mail.gmail.com>
On 21.01.2011 18:58, Peter Maydell wrote:
> I've reviewed this patch and tested it in the usual way
> and can confirm that it now sets the right saturation bit;
> mostly it is OK. However...
Thanks!
[...]
> the indentation in this hunk is wrong -- qemu standard is four-space.
Oops. What is the "official" emacs configuration to get the right qemu style?
> You can check for this sort of thing by running scripts/checkpatch.pl,
Thanks for the pointer.
Here is an updated patch with these minor fixes.
Christophe.
Signed-off-by: Christophe Lyon <christophe.lyon@st.com>
---
target-arm/helpers.h | 12 ++++--
target-arm/neon_helper.c | 89 ++++++++++++++++++++++++++++++++++++++++++++++
target-arm/op_helper.c | 49 -------------------------
target-arm/translate.c | 18 ++++-----
4 files changed, 105 insertions(+), 63 deletions(-)
diff --git a/target-arm/helpers.h b/target-arm/helpers.h
index b88ebae..8a2564e 100644
--- a/target-arm/helpers.h
+++ b/target-arm/helpers.h
@@ -137,10 +137,6 @@ DEF_HELPER_2(rsqrte_f32, f32, f32, env)
DEF_HELPER_2(recpe_u32, i32, i32, env)
DEF_HELPER_2(rsqrte_u32, i32, i32, env)
DEF_HELPER_4(neon_tbl, i32, i32, i32, i32, i32)
-DEF_HELPER_2(neon_add_saturate_u64, i64, i64, i64)
-DEF_HELPER_2(neon_add_saturate_s64, i64, i64, i64)
-DEF_HELPER_2(neon_sub_saturate_u64, i64, i64, i64)
-DEF_HELPER_2(neon_sub_saturate_s64, i64, i64, i64)
DEF_HELPER_2(add_cc, i32, i32, i32)
DEF_HELPER_2(adc_cc, i32, i32, i32)
@@ -160,10 +156,18 @@ DEF_HELPER_3(neon_qadd_u8, i32, env, i32, i32)
DEF_HELPER_3(neon_qadd_s8, i32, env, i32, i32)
DEF_HELPER_3(neon_qadd_u16, i32, env, i32, i32)
DEF_HELPER_3(neon_qadd_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_s32, i32, env, i32, i32)
DEF_HELPER_3(neon_qsub_u8, i32, env, i32, i32)
DEF_HELPER_3(neon_qsub_s8, i32, env, i32, i32)
DEF_HELPER_3(neon_qsub_u16, i32, env, i32, i32)
DEF_HELPER_3(neon_qsub_s16, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_u32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qsub_s32, i32, env, i32, i32)
+DEF_HELPER_3(neon_qadd_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qadd_s64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qsub_u64, i64, env, i64, i64)
+DEF_HELPER_3(neon_qsub_s64, i64, env, i64, i64)
DEF_HELPER_2(neon_hadd_s8, i32, i32, i32)
DEF_HELPER_2(neon_hadd_u8, i32, i32, i32)
diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index 20f3c16..c1619c0 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -198,6 +198,28 @@ NEON_VOP_ENV(qadd_u16, neon_u16, 2)
#undef NEON_FN
#undef NEON_USAT
+uint32_t HELPER(neon_qadd_u32)(CPUState *env, uint32_t a, uint32_t b)
+{
+ uint32_t res = a + b;
+ if (res < a) {
+ SET_QC();
+ res = ~0;
+ }
+ return res;
+}
+
+uint64_t HELPER(neon_qadd_u64)(CPUState *env, uint64_t src1, uint64_t src2)
+{
+ uint64_t res;
+
+ res = src1 + src2;
+ if (res < src1) {
+ SET_QC();
+ res = ~(uint64_t)0;
+ }
+ return res;
+}
+
#define NEON_SSAT(dest, src1, src2, type) do { \
int32_t tmp = (uint32_t)src1 + (uint32_t)src2; \
if (tmp != (type)tmp) { \
@@ -218,6 +240,28 @@ NEON_VOP_ENV(qadd_s16, neon_s16, 2)
#undef NEON_FN
#undef NEON_SSAT
+uint32_t HELPER(neon_qadd_s32)(CPUState *env, uint32_t a, uint32_t b)
+{
+ uint32_t res = a + b;
+ if (((res ^ a) & SIGNBIT) && !((a ^ b) & SIGNBIT)) {
+ SET_QC();
+ res = ~(((int32_t)a >> 31) ^ SIGNBIT);
+ }
+ return res;
+}
+
+uint64_t HELPER(neon_qadd_s64)(CPUState *env, uint64_t src1, uint64_t src2)
+{
+ uint64_t res;
+
+ res = src1 + src2;
+ if (((res ^ src1) & SIGNBIT64) && !((src1 ^ src2) & SIGNBIT64)) {
+ SET_QC();
+ res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;
+ }
+ return res;
+}
+
#define NEON_USAT(dest, src1, src2, type) do { \
uint32_t tmp = (uint32_t)src1 - (uint32_t)src2; \
if (tmp != (type)tmp) { \
@@ -234,6 +278,29 @@ NEON_VOP_ENV(qsub_u16, neon_u16, 2)
#undef NEON_FN
#undef NEON_USAT
+uint32_t HELPER(neon_qsub_u32)(CPUState *env, uint32_t a, uint32_t b)
+{
+ uint32_t res = a - b;
+ if (res > a) {
+ SET_QC();
+ res = 0;
+ }
+ return res;
+}
+
+uint64_t HELPER(neon_qsub_u64)(CPUState *env, uint64_t src1, uint64_t src2)
+{
+ uint64_t res;
+
+ if (src1 < src2) {
+ SET_QC();
+ res = 0;
+ } else {
+ res = src1 - src2;
+ }
+ return res;
+}
+
#define NEON_SSAT(dest, src1, src2, type) do { \
int32_t tmp = (uint32_t)src1 - (uint32_t)src2; \
if (tmp != (type)tmp) { \
@@ -254,6 +321,28 @@ NEON_VOP_ENV(qsub_s16, neon_s16, 2)
#undef NEON_FN
#undef NEON_SSAT
+uint32_t HELPER(neon_qsub_s32)(CPUState *env, uint32_t a, uint32_t b)
+{
+ uint32_t res = a - b;
+ if (((res ^ a) & SIGNBIT) && ((a ^ b) & SIGNBIT)) {
+ SET_QC();
+ res = ~(((int32_t)a >> 31) ^ SIGNBIT);
+ }
+ return res;
+}
+
+uint64_t HELPER(neon_qsub_s64)(CPUState *env, uint64_t src1, uint64_t src2)
+{
+ uint64_t res;
+
+ res = src1 - src2;
+ if (((res ^ src1) & SIGNBIT64) && ((src1 ^ src2) & SIGNBIT64)) {
+ SET_QC();
+ res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;
+ }
+ return res;
+}
+
#define NEON_FN(dest, src1, src2) dest = (src1 + src2) >> 1
NEON_VOP(hadd_s8, neon_s8, 4)
NEON_VOP(hadd_u8, neon_u8, 4)
diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c
index 43baa63..3de2610 100644
--- a/target-arm/op_helper.c
+++ b/target-arm/op_helper.c
@@ -424,52 +424,3 @@ uint32_t HELPER(ror_cc)(uint32_t x, uint32_t i)
return ((uint32_t)x >> shift) | (x << (32 - shift));
}
}
-
-uint64_t HELPER(neon_add_saturate_s64)(uint64_t src1, uint64_t src2)
-{
- uint64_t res;
-
- res = src1 + src2;
- if (((res ^ src1) & SIGNBIT64) && !((src1 ^ src2) & SIGNBIT64)) {
- env->QF = 1;
- res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;
- }
- return res;
-}
-
-uint64_t HELPER(neon_add_saturate_u64)(uint64_t src1, uint64_t src2)
-{
- uint64_t res;
-
- res = src1 + src2;
- if (res < src1) {
- env->QF = 1;
- res = ~(uint64_t)0;
- }
- return res;
-}
-
-uint64_t HELPER(neon_sub_saturate_s64)(uint64_t src1, uint64_t src2)
-{
- uint64_t res;
-
- res = src1 - src2;
- if (((res ^ src1) & SIGNBIT64) && ((src1 ^ src2) & SIGNBIT64)) {
- env->QF = 1;
- res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;
- }
- return res;
-}
-
-uint64_t HELPER(neon_sub_saturate_u64)(uint64_t src1, uint64_t src2)
-{
- uint64_t res;
-
- if (src1 < src2) {
- env->QF = 1;
- res = 0;
- } else {
- res = src1 - src2;
- }
- return res;
-}
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 41cbb96..ab4aa29 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3539,12 +3539,6 @@ static inline void gen_neon_rsb(int size, TCGv t0, TCGv t1)
#define gen_helper_neon_pmin_s32 gen_helper_neon_min_s32
#define gen_helper_neon_pmin_u32 gen_helper_neon_min_u32
-/* FIXME: This is wrong. They set the wrong overflow bit. */
-#define gen_helper_neon_qadd_s32(a, e, b, c) gen_helper_add_saturate(a, b, c)
-#define gen_helper_neon_qadd_u32(a, e, b, c) gen_helper_add_usaturate(a, b, c)
-#define gen_helper_neon_qsub_s32(a, e, b, c) gen_helper_sub_saturate(a, b, c)
-#define gen_helper_neon_qsub_u32(a, e, b, c) gen_helper_sub_usaturate(a, b, c)
-
#define GEN_NEON_INTEGER_OP_ENV(name) do { \
switch ((size << 1) | u) { \
case 0: \
@@ -4233,16 +4227,20 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
switch (op) {
case 1: /* VQADD */
if (u) {
- gen_helper_neon_add_saturate_u64(CPU_V001);
+ gen_helper_neon_qadd_u64(cpu_V0, cpu_env,
+ cpu_V0, cpu_V1);
} else {
- gen_helper_neon_add_saturate_s64(CPU_V001);
+ gen_helper_neon_qadd_s64(cpu_V0, cpu_env,
+ cpu_V0, cpu_V1);
}
break;
case 5: /* VQSUB */
if (u) {
- gen_helper_neon_sub_saturate_u64(CPU_V001);
+ gen_helper_neon_qsub_u64(cpu_V0, cpu_env,
+ cpu_V0, cpu_V1);
} else {
- gen_helper_neon_sub_saturate_s64(CPU_V001);
+ gen_helper_neon_qsub_s64(cpu_V0, cpu_env,
+ cpu_V0, cpu_V1);
}
break;
case 8: /* VSHL */
--
1.7.2.3
next prev parent reply other threads:[~2011-01-24 12:42 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-01-20 17:16 [Qemu-devel] [PATCH] target-arm: Set the right overflow bit for neon 32 and 64 bit saturating add/sub Christophe Lyon
2011-01-20 17:51 ` Peter Maydell
2011-01-21 17:58 ` Peter Maydell
2011-01-24 12:41 ` Christophe Lyon [this message]
2011-01-24 12:59 ` Peter Maydell
2011-01-31 15:47 ` Christophe Lyon
2011-02-04 11:27 ` 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=4D3D738E.5040709@st.com \
--to=christophe.lyon@st.com \
--cc=peter.maydell@linaro.org \
--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.