From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-arm@nongnu.org, qemu-devel@nongnu.org
Subject: [PATCH for-6.2 36/53] target/arm: Implement MVE VADD (floating-point)
Date: Thu, 29 Jul 2021 12:14:55 +0100 [thread overview]
Message-ID: <20210729111512.16541-37-peter.maydell@linaro.org> (raw)
In-Reply-To: <20210729111512.16541-1-peter.maydell@linaro.org>
Implement the MVE VADD (floating-point) insn. Handling of this is
similar to the 2-operand integer insns, except that we must take care
to only update the floating point exception status if the least
significant bit of the predicate mask for each element is active.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/helper-mve.h | 3 +++
target/arm/translate.h | 6 ++++++
target/arm/mve.decode | 10 ++++++++++
target/arm/mve_helper.c | 37 +++++++++++++++++++++++++++++++++++++
target/arm/translate-mve.c | 17 +++++++++++++++++
target/arm/translate-neon.c | 6 ------
6 files changed, 73 insertions(+), 6 deletions(-)
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 3db9b15f121..32fd2e1f9be 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -410,6 +410,9 @@ DEF_HELPER_FLAGS_4(mve_vhcadd270b, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
DEF_HELPER_FLAGS_4(mve_vhcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
DEF_HELPER_FLAGS_4(mve_vhcadd270w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vfaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vfadds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/translate.h b/target/arm/translate.h
index 241596c5bda..8636c20c3b4 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -181,6 +181,12 @@ static inline int rsub_8(DisasContext *s, int x)
return 8 - x;
}
+static inline int neon_3same_fp_size(DisasContext *s, int x)
+{
+ /* Convert 0==fp32, 1==fp16 into a MO_* value */
+ return MO_32 - x;
+}
+
static inline int arm_dc_feature(DisasContext *dc, int feature)
{
return (dc->features & (1ULL << feature)) != 0;
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 87446816293..e211cb016c6 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -26,6 +26,10 @@
# VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit
%size_28 28:1 !function=plus_1
+# 2 operand fp insns have size in bit 20: 1 for 16 bit, 0 for 32 bit,
+# like Neon FP insns.
+%2op_fp_size 20:1 !function=neon_3same_fp_size
+
# 1imm format immediate
%imm_28_16_0 28:1 16:3 0:4
@@ -118,6 +122,9 @@
@vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm
+@2op_fp .... .... .... .... .... .... .... .... &2op \
+ qd=%qd qn=%qn qm=%qm size=%2op_fp_size
+
# Vector loads and stores
# Widening loads and narrowing stores:
@@ -615,3 +622,6 @@ VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar
VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar
VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar
VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar
+
+# 2-operand FP
+VADD_fp 1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index c2826eb5f9f..ff087e9d3a4 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -25,6 +25,7 @@
#include "exec/cpu_ldst.h"
#include "exec/exec-all.h"
#include "tcg/tcg.h"
+#include "fpu/softfloat.h"
static uint16_t mve_eci_mask(CPUARMState *env)
{
@@ -2798,3 +2799,39 @@ DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX)
DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN)
DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN)
DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN)
+
+/*
+ * 2-operand floating point. Note that if an element is partially
+ * predicated we must do the FP operation to update the non-predicated
+ * bytes, but we must be careful to avoid updating the FP exception
+ * state unless byte 0 of the element was unpredicated.
+ */
+#define DO_2OP_FP(OP, ESIZE, TYPE, FN) \
+ void HELPER(glue(mve_, OP))(CPUARMState *env, \
+ void *vd, void *vn, void *vm) \
+ { \
+ TYPE *d = vd, *n = vn, *m = vm; \
+ TYPE r; \
+ uint16_t mask = mve_element_mask(env); \
+ unsigned e; \
+ float_status *fpst; \
+ float_status scratch_fpst; \
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
+ if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \
+ continue; \
+ } \
+ fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \
+ &env->vfp.standard_fp_status; \
+ if (!(mask & 1)) { \
+ /* We need the result but without updating flags */ \
+ scratch_fpst = *fpst; \
+ fpst = &scratch_fpst; \
+ } \
+ r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \
+ mergemask(&d[H##ESIZE(e)], r, mask); \
+ } \
+ mve_advance_vpt(env); \
+ }
+
+DO_2OP_FP(vfaddh, 2, uint16_t, float16_add)
+DO_2OP_FP(vfadds, 4, uint32_t, float32_add)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 78229c44c68..d2c40ede564 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -831,6 +831,23 @@ static bool trans_VSBCI(DisasContext *s, arg_2op *a)
return do_2op(s, a, gen_helper_mve_vsbci);
}
+#define DO_2OP_FP(INSN, FN) \
+ static bool trans_##INSN(DisasContext *s, arg_2op *a) \
+ { \
+ static MVEGenTwoOpFn * const fns[] = { \
+ NULL, \
+ gen_helper_mve_##FN##h, \
+ gen_helper_mve_##FN##s, \
+ NULL, \
+ }; \
+ if (!dc_isar_feature(aa32_mve_fp, s)) { \
+ return false; \
+ } \
+ return do_2op(s, a, fns[a->size]); \
+ }
+
+DO_2OP_FP(VADD_fp, vfadd)
+
static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
MVEGenTwoOpScalarFn fn)
{
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index c53ab20fa48..dd43de558e4 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -28,12 +28,6 @@
#include "translate.h"
#include "translate-a32.h"
-static inline int neon_3same_fp_size(DisasContext *s, int x)
-{
- /* Convert 0==fp32, 1==fp16 into a MO_* value */
- return MO_32 - x;
-}
-
/* Include the generated Neon decoder */
#include "decode-neon-dp.c.inc"
#include "decode-neon-ls.c.inc"
--
2.20.1
next prev parent reply other threads:[~2021-07-29 11:36 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-29 11:14 [PATCH for-6.2 00/53] target/arm: MVE slices 3 and 4 Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 01/53] target/arm: Note that we handle VMOVL as a special case of VSHLL Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 02/53] target/arm: Print MVE VPR in CPU dumps Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 03/53] target/arm: Fix MVE VSLI by 0 and VSRI by <dt> Peter Maydell
2021-07-30 18:56 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 04/53] target/arm: Fix signed VADDV Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 05/53] target/arm: Fix mask handling for MVE narrowing operations Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 06/53] target/arm: Fix 48-bit saturating shifts Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 07/53] target/arm: Fix MVE 48-bit SQRSHRL for small right shifts Peter Maydell
2021-07-30 19:07 ` Richard Henderson
2021-08-12 9:43 ` Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 08/53] target/arm: Fix calculation of LTP mask when LR is 0 Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 09/53] target/arm: Factor out mve_eci_mask() Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 10/53] target/arm: Fix VPT advance when ECI is non-zero Peter Maydell
2021-07-30 19:14 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 11/53] target/arm: Fix VLDRB/H/W for predicated elements Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 12/53] target/arm: Implement MVE VMULL (polynomial) Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 13/53] target/arm: Implement MVE incrementing/decrementing dup insns Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 14/53] target/arm: Factor out gen_vpst() Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 15/53] target/arm: Implement MVE integer vector comparisons Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 16/53] target/arm: Implement MVE integer vector-vs-scalar comparisons Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 17/53] target/arm: Implement MVE VPSEL Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 18/53] target/arm: Implement MVE VMLAS Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 19/53] target/arm: Implement MVE shift-by-scalar Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 20/53] target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 21/53] target/arm: Implement MVE integer min/max across vector Peter Maydell
2021-07-30 19:15 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 22/53] target/arm: Implement MVE VABAV Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 23/53] target/arm: Implement MVE narrowing moves Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 24/53] target/arm: Rename MVEGenDualAccOpFn to MVEGenLongDualAccOpFn Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 25/53] target/arm: Implement MVE VMLADAV and VMLSLDAV Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 26/53] target/arm: Implement MVE VMLA Peter Maydell
2021-07-30 19:18 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 27/53] target/arm: Implement MVE saturating doubling multiply accumulates Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 28/53] target/arm: Implement MVE VQABS, VQNEG Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 29/53] target/arm: Implement MVE VMAXA, VMINA Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 30/53] target/arm: Implement MVE VMOV to/from 2 general-purpose registers Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 31/53] target/arm: Implement MVE VPNOT Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 32/53] target/arm: Implement MVE VCTP Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 33/53] target/arm: Implement MVE scatter-gather insns Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 34/53] target/arm: Implement MVE scatter-gather immediate forms Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 35/53] target/arm: Implement MVE interleaving loads/stores Peter Maydell
2021-07-29 11:14 ` Peter Maydell [this message]
2021-07-30 19:27 ` [PATCH for-6.2 36/53] target/arm: Implement MVE VADD (floating-point) Richard Henderson
2021-07-30 19:37 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 37/53] target/arm: Implement MVE VSUB, VMUL, VABD, VMAXNM, VMINNM Peter Maydell
2021-07-30 19:28 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 38/53] target/arm: Implement MVE VCADD Peter Maydell
2021-07-30 19:32 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 39/53] target/arm: Implement MVE VFMA and VFMS Peter Maydell
2021-07-30 19:34 ` Richard Henderson
2021-07-30 19:41 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 40/53] target/arm: Implement MVE VCMUL and VCMLA Peter Maydell
2021-07-30 19:47 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 41/53] target/arm: Implement MVE VMAXNMA and VMINNMA Peter Maydell
2021-07-30 19:50 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 42/53] target/arm: Implement MVE scalar fp insns Peter Maydell
2021-07-30 19:55 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 43/53] target/arm: Implement MVE fp-with-scalar VFMA, VFMAS Peter Maydell
2021-07-30 19:58 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 44/53] softfloat: Remove assertion preventing silencing of NaN in default-NaN mode Peter Maydell
2021-07-30 20:00 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 45/53] target/arm: Implement MVE FP max/min across vector Peter Maydell
2021-07-30 20:12 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 46/53] target/arm: Implement MVE fp vector comparisons Peter Maydell
2021-07-30 20:21 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 47/53] target/arm: Implement MVE fp scalar comparisons Peter Maydell
2021-07-30 20:22 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 48/53] target/arm: Implement MVE VCVT between floating and fixed point Peter Maydell
2021-07-30 20:24 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 49/53] target/arm: Implement MVE VCVT between fp and integer Peter Maydell
2021-07-30 20:27 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 50/53] target/arm: Implement MVE VCVT with specified rounding mode Peter Maydell
2021-07-30 20:28 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 51/53] target/arm: Implement MVE VCVT between single and half precision Peter Maydell
2021-07-30 20:33 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 52/53] target/arm: Implement MVE VRINT insns Peter Maydell
2021-07-30 20:47 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 53/53] target/arm: Enable MVE in Cortex-M55 Peter Maydell
2021-07-30 20:48 ` 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=20210729111512.16541-37-peter.maydell@linaro.org \
--to=peter.maydell@linaro.org \
--cc=qemu-arm@nongnu.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 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).