All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-devel@nongnu.org
Subject: [PULL 09/51] target/arm: Implement MVE VFMA and VFMS
Date: Wed,  1 Sep 2021 11:36:11 +0100	[thread overview]
Message-ID: <20210901103653.13435-10-peter.maydell@linaro.org> (raw)
In-Reply-To: <20210901103653.13435-1-peter.maydell@linaro.org>

Implement the MVE VFMA and VFMS insns.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-mve.h    |  6 ++++++
 target/arm/mve.decode      |  3 +++
 target/arm/mve_helper.c    | 37 +++++++++++++++++++++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 48 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 42eba8ea96d..c230610d25c 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -434,6 +434,12 @@ DEF_HELPER_FLAGS_4(mve_vfcadd90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vfcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vfcadd270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vfmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vfmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vfmsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vfmss, 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/mve.decode b/target/arm/mve.decode
index c728c7089ac..3a2056f6b34 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -639,3 +639,6 @@ VMINNM            1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp
 
 VCADD90_fp        1111 1100 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
 VCADD270_fp       1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
+
+VFMA              1110 1111 0 . 0 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp
+VFMS              1110 1111 0 . 1 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 2cc8b3e11b7..d7f250a4455 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -2894,3 +2894,40 @@ DO_VCADD_FP(vfcadd90h, 2, float16, float16_sub, float16_add)
 DO_VCADD_FP(vfcadd90s, 4, float32, float32_sub, float32_add)
 DO_VCADD_FP(vfcadd270h, 2, float16, float16_add, float16_sub)
 DO_VCADD_FP(vfcadd270s, 4, float32, float32_add, float32_sub)
+
+#define DO_VFMA(OP, ESIZE, TYPE, CHS)                                   \
+    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 = n[H##ESIZE(e)];                                         \
+            if (CHS) {                                                  \
+                r = TYPE##_chs(r);                                      \
+            }                                                           \
+            r = TYPE##_muladd(r, m[H##ESIZE(e)], d[H##ESIZE(e)],        \
+                              0, fpst);                                 \
+            mergemask(&d[H##ESIZE(e)], r, mask);                        \
+        }                                                               \
+        mve_advance_vpt(env);                                           \
+    }
+
+DO_VFMA(vfmah, 2, float16, false)
+DO_VFMA(vfmas, 4, float32, false)
+DO_VFMA(vfmsh, 2, float16, true)
+DO_VFMA(vfmss, 4, float32, true)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 6203e3ff916..d61abc6d46f 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -854,6 +854,8 @@ DO_2OP_FP(VMAXNM, vmaxnm)
 DO_2OP_FP(VMINNM, vminnm)
 DO_2OP_FP(VCADD90_fp, vfcadd90)
 DO_2OP_FP(VCADD270_fp, vfcadd270)
+DO_2OP_FP(VFMA, vfma)
+DO_2OP_FP(VFMS, vfms)
 
 static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
                           MVEGenTwoOpScalarFn fn)
-- 
2.20.1



  parent reply	other threads:[~2021-09-01 10:48 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-01 10:36 [PULL 00/51] target-arm queue Peter Maydell
2021-09-01 10:36 ` [PULL 01/51] tests: Remove uses of deprecated raspi2/raspi3 machine names Peter Maydell
2021-09-01 10:36 ` [PULL 02/51] hw/arm/raspi: Remove deprecated raspi2/raspi3 aliases Peter Maydell
2021-09-01 10:36 ` [PULL 03/51] hw/intc/arm_gicv3_dist: Rename 64-bit accessors with 'q' suffix Peter Maydell
2021-09-01 10:36 ` [PULL 04/51] hw/intc/arm_gicv3: Replace mis-used MEMTX_* constants by booleans Peter Maydell
2021-09-01 10:36 ` [PULL 05/51] hw: Add compat machines for 6.2 Peter Maydell
2021-09-01 10:36 ` [PULL 06/51] target/arm: Implement MVE VADD (floating-point) Peter Maydell
2021-09-01 10:36 ` [PULL 07/51] target/arm: Implement MVE VSUB, VMUL, VABD, VMAXNM, VMINNM Peter Maydell
2021-09-01 10:36 ` [PULL 08/51] target/arm: Implement MVE VCADD Peter Maydell
2021-09-01 10:36 ` Peter Maydell [this message]
2021-09-01 10:36 ` [PULL 10/51] target/arm: Implement MVE VCMUL and VCMLA Peter Maydell
2021-09-01 10:36 ` [PULL 11/51] target/arm: Implement MVE VMAXNMA and VMINNMA Peter Maydell
2021-09-01 10:36 ` [PULL 12/51] target/arm: Implement MVE scalar fp insns Peter Maydell
2021-09-01 10:36 ` [PULL 13/51] target/arm: Implement MVE fp-with-scalar VFMA, VFMAS Peter Maydell
2021-09-01 10:36 ` [PULL 14/51] softfloat: Remove assertion preventing silencing of NaN in default-NaN mode Peter Maydell
2021-09-01 10:36 ` [PULL 15/51] target/arm: Implement MVE FP max/min across vector Peter Maydell
2021-09-01 10:36 ` [PULL 16/51] target/arm: Implement MVE fp vector comparisons Peter Maydell
2021-09-01 10:36 ` [PULL 17/51] target/arm: Implement MVE fp scalar comparisons Peter Maydell
2021-09-01 10:36 ` [PULL 18/51] target/arm: Implement MVE VCVT between floating and fixed point Peter Maydell
2021-09-01 10:36 ` [PULL 19/51] target/arm: Implement MVE VCVT between fp and integer Peter Maydell
2021-09-01 10:36 ` [PULL 20/51] target/arm: Implement MVE VCVT with specified rounding mode Peter Maydell
2021-09-01 10:36 ` [PULL 21/51] target/arm: Implement MVE VCVT between single and half precision Peter Maydell
2021-09-01 10:36 ` [PULL 22/51] target/arm: Implement MVE VRINT insns Peter Maydell
2021-09-01 10:36 ` [PULL 23/51] target/arm: Enable MVE in Cortex-M55 Peter Maydell
2021-09-01 10:36 ` [PULL 24/51] target-arm: Add support for Fujitsu A64FX Peter Maydell
2021-09-01 10:36 ` [PULL 25/51] hw/arm/virt: target-arm: Add A64FX processor support to virt machine Peter Maydell
2021-09-01 10:36 ` [PULL 26/51] tests/arm-cpu-features: Add A64FX processor related tests Peter Maydell
2021-09-01 10:36 ` [PULL 27/51] arm: Move M-profile RAS register block into its own device Peter Maydell
2021-09-01 10:36 ` [PULL 28/51] arm: Move systick device creation from NVIC to ARMv7M object Peter Maydell
2021-09-01 10:36 ` [PULL 29/51] arm: Move system PPB container handling to armv7m Peter Maydell
2021-09-01 10:36 ` [PULL 30/51] hw/timer/armv7m_systick: Add usual QEMU interface comment Peter Maydell
2021-09-01 10:36 ` [PULL 31/51] hw/timer/armv7m_systick: Add input clocks Peter Maydell
2021-09-01 10:36 ` [PULL 32/51] hw/arm/armv7m: Create " Peter Maydell
2021-09-01 10:36 ` [PULL 33/51] armsse: Wire up systick cpuclk clock Peter Maydell
2021-09-01 10:36 ` [PULL 34/51] hw/arm/mps2.c: Connect up armv7m clocks Peter Maydell
2021-09-01 10:36 ` [PULL 35/51] clock: Provide builtin multiplier/divider Peter Maydell
2021-09-01 10:36 ` [PULL 36/51] hw/arm: Don't allocate separate MemoryRegions in stm32 SoC realize Peter Maydell
2021-09-01 10:36 ` [PULL 37/51] hw/arm/stm32f100: Wire up sysclk and refclk Peter Maydell
2021-09-01 10:36 ` [PULL 38/51] hw/arm/stm32f205: " Peter Maydell
2021-09-01 10:36 ` [PULL 39/51] hw/arm/stm32f405: " Peter Maydell
2021-09-01 10:36 ` [PULL 40/51] hw/arm/stm32vldiscovery: Delete trailing blank line Peter Maydell
2021-09-01 10:36 ` [PULL 41/51] hw/arm/nrf51: Wire up sysclk Peter Maydell
2021-09-01 10:36 ` [PULL 42/51] hw/arm/stellaris: split stellaris_sys_init() Peter Maydell
2021-09-01 10:36 ` [PULL 43/51] hw/arm/stellaris: Wire sysclk up to armv7m Peter Maydell
2021-09-01 10:36 ` [PULL 44/51] hw/arm/msf2_soc: Don't allocate separate MemoryRegions Peter Maydell
2021-09-01 10:36 ` [PULL 45/51] hw/arm/msf2: Use Clock input to MSF2_SOC instead of m3clk property Peter Maydell
2021-09-01 10:36 ` [PULL 46/51] hw/arm/msf2-soc: Wire up refclk Peter Maydell
2021-09-01 10:36 ` [PULL 47/51] hw/timer/armv7m_systick: Use clock inputs instead of system_clock_scale Peter Maydell
2021-09-01 10:36 ` [PULL 48/51] hw/arm/stellaris: Fix code style issues in GPTM code Peter Maydell
2021-09-01 10:36 ` [PULL 49/51] hw/arm/stellaris: Split stellaris-gptm into its own file Peter Maydell
2021-09-01 10:36 ` [PULL 50/51] hw/timer/stellaris-gptm: Use Clock input instead of system_clock_scale Peter Maydell
2021-09-01 10:36 ` [PULL 51/51] arm: Remove system_clock_scale global Peter Maydell
2021-09-02  7:48 ` [PULL 00/51] target-arm queue 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=20210901103653.13435-10-peter.maydell@linaro.org \
    --to=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --subject='Re: [PULL 09/51] target/arm: Implement MVE VFMA and VFMS' \
    /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

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.