[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 09/18] target/arm: Implement MVE VSHLL
|
From: |
Peter Maydell |
|
Subject: |
[PATCH 09/18] target/arm: Implement MVE VSHLL |
|
Date: |
Mon, 28 Jun 2021 14:58:26 +0100 |
Implement the MVE VHLL (vector shift left long) insn. This has two
encodings: the T1 encoding is the usual shift-by-immediate format,
and the T2 encoding is a special case where the shift count is always
equal to the element size.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/helper-mve.h | 9 +++++++
target/arm/mve.decode | 53 +++++++++++++++++++++++++++++++++++---
target/arm/mve_helper.c | 32 +++++++++++++++++++++++
target/arm/translate-mve.c | 15 +++++++++++
4 files changed, 105 insertions(+), 4 deletions(-)
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 288a8faf4e8..8af0e7fd8cf 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -387,3 +387,12 @@ DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void,
env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshllbuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 8be04589a6c..6e6032b25a7 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -64,6 +64,14 @@
@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm
size=1
@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm
size=2
+@2_shll_b .... .... ... 01 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm
size=0
+@2_shll_h .... .... ... 1 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm
size=1
+# VSHLL encoding T2 where shift == esize
+@2_shll_esize_b .... .... .... 00 .. .... .... .... .... &2shift \
+ qd=%qd qm=%qm size=0 shift=8
+@2_shll_esize_h .... .... .... 01 .. .... .... .... .... &2shift \
+ qd=%qd qm=%qm size=1 shift=16
+
# Right shifts are encoded as N - shift, where N is the element size in bits.
%rshift_i5 16:5 !function=rsub_32
%rshift_i4 16:4 !function=rsub_16
@@ -122,11 +130,35 @@ VADD 1110 1111 0 . .. ... 0 ... 0 1000 . 1 .
0 ... 0 @2op
VSUB 1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
-VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
-VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
+# The VSHLL T2 encoding is not a @2op pattern, but is here because it
+# overlaps what would be size=0b11 VMULH/VRMULH
+{
+ VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1
@2_shll_esize_b
+ VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1
@2_shll_esize_h
-VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
-VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
+ VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
+}
+
+{
+ VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1
@2_shll_esize_b
+ VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1
@2_shll_esize_h
+
+ VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
+}
+
+{
+ VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1
@2_shll_esize_b
+ VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1
@2_shll_esize_h
+
+ VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
+}
+
+{
+ VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1
@2_shll_esize_b
+ VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1
@2_shll_esize_h
+
+ VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
+}
VMAX_S 111 0 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
VMAX_U 111 1 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
@@ -326,3 +358,16 @@ VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 .
1 ... 0 @2_shr_w
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
+
+# VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file
+VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
+VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
+
+VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
+VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
+
+VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
+VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
+
+VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
+VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index ac720c9ee05..8798e77cba8 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1250,3 +1250,35 @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP)
DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
+
+/*
+ * Long shifts taking half-sized inputs from top or bottom of the input
+ * vector and producing a double-width result. ESIZE, TYPE are for
+ * the input, and LESIZE, LTYPE for the output.
+ * Unlike the normal shift helpers, we do not handle negative shift counts,
+ * because the long shift is strictly left-only.
+ */
+#define DO_VSHLL(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
+ void *vm, uint32_t shift) \
+ { \
+ LTYPE *d = vd; \
+ TYPE *m = vm; \
+ uint16_t mask = mve_element_mask(env); \
+ unsigned le; \
+ assert(shift <= 16); \
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
+ LTYPE r = (LTYPE)m[H##ESIZE(le * 2 + TOP)] << shift; \
+ mergemask(&d[H##LESIZE(le)], r, mask); \
+ } \
+ mve_advance_vpt(env); \
+ }
+
+#define DO_VSHLL_ALL(OP, TOP) \
+ DO_VSHLL(OP##sb, TOP, 1, int8_t, 2, int16_t) \
+ DO_VSHLL(OP##ub, TOP, 1, uint8_t, 2, uint16_t) \
+ DO_VSHLL(OP##sh, TOP, 2, int16_t, 4, int32_t) \
+ DO_VSHLL(OP##uh, TOP, 2, uint16_t, 4, uint32_t) \
+
+DO_VSHLL_ALL(vshllb, false)
+DO_VSHLL_ALL(vshllt, true)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 4030ee07f0d..044462c3752 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -893,3 +893,18 @@ DO_2SHIFT(VSHRI_S, vshli_s, true)
DO_2SHIFT(VSHRI_U, vshli_u, true)
DO_2SHIFT(VRSHRI_S, vrshli_s, true)
DO_2SHIFT(VRSHRI_U, vrshli_u, true)
+
+#define DO_VSHLL(INSN, FN) \
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
+ { \
+ static MVEGenTwoOpShiftFn * const fns[] = { \
+ gen_helper_mve_##FN##b, \
+ gen_helper_mve_##FN##h, \
+ }; \
+ return do_2shift(s, a, fns[a->size], false); \
+ }
+
+DO_VSHLL(VSHLL_BS, vshllbs)
+DO_VSHLL(VSHLL_BU, vshllbu)
+DO_VSHLL(VSHLL_TS, vshllts)
+DO_VSHLL(VSHLL_TU, vshlltu)
--
2.20.1
- Re: [PATCH 06/18] target/arm: Implement MVE logical immediate insns, (continued)
- [PATCH 04/18] target/arm: Use asimd_imm_const for A64 decode, Peter Maydell, 2021/06/28
- [PATCH 07/18] target/arm: Implement MVE vector shift left by immediate insns, Peter Maydell, 2021/06/28
- [PATCH 08/18] target/arm: Implement MVE vector shift right by immediate insns, Peter Maydell, 2021/06/28
- [PATCH 16/18] target/arm: Implement MVE long shifts by register, Peter Maydell, 2021/06/28
- [PATCH 09/18] target/arm: Implement MVE VSHLL,
Peter Maydell <=
- [PATCH 17/18] target/arm: Implement MVE shifts by immediate, Peter Maydell, 2021/06/28
- [PATCH 13/18] target/arm: Implement MVE VSHLC, Peter Maydell, 2021/06/28
- [PATCH 12/18] target/arm: Implement MVE saturating narrowing shifts, Peter Maydell, 2021/06/28
- [PATCH 18/18] target/arm: Implement MVE shifts by register, Peter Maydell, 2021/06/28
- [PATCH 15/18] target/arm: Implement MVE long shifts by immediate, Peter Maydell, 2021/06/28