[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 12/18] target/arm: Implement MVE saturating narrowing shifts
|
From: |
Peter Maydell |
|
Subject: |
[PATCH 12/18] target/arm: Implement MVE saturating narrowing shifts |
|
Date: |
Mon, 28 Jun 2021 14:58:29 +0100 |
Implement the MVE saturating shift-right-and-narrow insns
VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN.
do_srshr() is borrowed from sve_helper.c.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/helper-mve.h | 30 +++++++++++
target/arm/mve.decode | 28 ++++++++++
target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++
target/arm/translate-mve.c | 12 +++++
4 files changed, 174 insertions(+)
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 323ac07fa35..96b4c0dfd34 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -414,3 +414,33 @@ DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void,
env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index e2c177f56a2..1d11387bc07 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -391,3 +391,31 @@ VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 .
0 ... 1 @2_shr_b
VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
+
+VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b
+VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h
+VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b
+VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h
+VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b
+VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h
+VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b
+VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h
+
+VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b
+VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h
+VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b
+VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h
+
+VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b
+VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h
+VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b
+VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h
+VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b
+VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h
+VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b
+VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h
+
+VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b
+VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h
+VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b
+VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index a97942208ba..3e736e89095 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1362,5 +1362,109 @@ static inline uint64_t do_urshr(uint64_t x, unsigned sh)
}
}
+static inline int64_t do_srshr(int64_t x, unsigned sh)
+{
+ if (likely(sh < 64)) {
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
+ } else {
+ /* Rounding the sign bit always produces 0. */
+ return 0;
+ }
+}
+
DO_VSHRN_ALL(vshrn, DO_SHR)
DO_VSHRN_ALL(vrshrn, do_urshr)
+
+static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max,
+ bool *satp)
+{
+ if (val > max) {
+ *satp = true;
+ return max;
+ } else if (val < min) {
+ *satp = true;
+ return min;
+ } else {
+ return val;
+ }
+}
+
+/* Saturating narrowing right shifts */
+#define DO_VSHRN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
+ void *vm, uint32_t shift) \
+ { \
+ LTYPE *m = vm; \
+ TYPE *d = vd; \
+ uint16_t mask = mve_element_mask(env); \
+ bool qc = false; \
+ unsigned le; \
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
+ bool sat = false; \
+ TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \
+ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \
+ qc |= sat && (mask & 1 << (TOP * ESIZE)); \
+ } \
+ if (qc) { \
+ env->vfp.qc[0] = qc; \
+ } \
+ mve_advance_vpt(env); \
+ }
+
+#define DO_VSHRN_SAT_UB(BOP, TOP, FN) \
+ DO_VSHRN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \
+ DO_VSHRN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN)
+
+#define DO_VSHRN_SAT_UH(BOP, TOP, FN) \
+ DO_VSHRN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \
+ DO_VSHRN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN)
+
+#define DO_VSHRN_SAT_SB(BOP, TOP, FN) \
+ DO_VSHRN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \
+ DO_VSHRN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN)
+
+#define DO_VSHRN_SAT_SH(BOP, TOP, FN) \
+ DO_VSHRN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \
+ DO_VSHRN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN)
+
+#define DO_SHRN_SB(N, M, SATP) \
+ do_sat_bhs((int64_t)(N) >> (M), INT8_MIN, INT8_MAX, SATP)
+#define DO_SHRN_UB(N, M, SATP) \
+ do_sat_bhs((uint64_t)(N) >> (M), 0, UINT8_MAX, SATP)
+#define DO_SHRUN_B(N, M, SATP) \
+ do_sat_bhs((int64_t)(N) >> (M), 0, UINT8_MAX, SATP)
+
+#define DO_SHRN_SH(N, M, SATP) \
+ do_sat_bhs((int64_t)(N) >> (M), INT16_MIN, INT16_MAX, SATP)
+#define DO_SHRN_UH(N, M, SATP) \
+ do_sat_bhs((uint64_t)(N) >> (M), 0, UINT16_MAX, SATP)
+#define DO_SHRUN_H(N, M, SATP) \
+ do_sat_bhs((int64_t)(N) >> (M), 0, UINT16_MAX, SATP)
+
+#define DO_RSHRN_SB(N, M, SATP) \
+ do_sat_bhs(do_srshr(N, M), INT8_MIN, INT8_MAX, SATP)
+#define DO_RSHRN_UB(N, M, SATP) \
+ do_sat_bhs(do_urshr(N, M), 0, UINT8_MAX, SATP)
+#define DO_RSHRUN_B(N, M, SATP) \
+ do_sat_bhs(do_srshr(N, M), 0, UINT8_MAX, SATP)
+
+#define DO_RSHRN_SH(N, M, SATP) \
+ do_sat_bhs(do_srshr(N, M), INT16_MIN, INT16_MAX, SATP)
+#define DO_RSHRN_UH(N, M, SATP) \
+ do_sat_bhs(do_urshr(N, M), 0, UINT16_MAX, SATP)
+#define DO_RSHRUN_H(N, M, SATP) \
+ do_sat_bhs(do_srshr(N, M), 0, UINT16_MAX, SATP)
+
+DO_VSHRN_SAT_SB(vqshrnb_sb, vqshrnt_sb, DO_SHRN_SB)
+DO_VSHRN_SAT_SH(vqshrnb_sh, vqshrnt_sh, DO_SHRN_SH)
+DO_VSHRN_SAT_UB(vqshrnb_ub, vqshrnt_ub, DO_SHRN_UB)
+DO_VSHRN_SAT_UH(vqshrnb_uh, vqshrnt_uh, DO_SHRN_UH)
+DO_VSHRN_SAT_SB(vqshrunbb, vqshruntb, DO_SHRUN_B)
+DO_VSHRN_SAT_SH(vqshrunbh, vqshrunth, DO_SHRUN_H)
+
+DO_VSHRN_SAT_SB(vqrshrnb_sb, vqrshrnt_sb, DO_RSHRN_SB)
+DO_VSHRN_SAT_SH(vqrshrnb_sh, vqrshrnt_sh, DO_RSHRN_SH)
+DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB)
+DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH)
+DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B)
+DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index f1a8f21b772..eef4f1f6ce3 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -926,3 +926,15 @@ DO_2SHIFT_N(VSHRNB, vshrnb)
DO_2SHIFT_N(VSHRNT, vshrnt)
DO_2SHIFT_N(VRSHRNB, vrshrnb)
DO_2SHIFT_N(VRSHRNT, vrshrnt)
+DO_2SHIFT_N(VQSHRNB_S, vqshrnb_s)
+DO_2SHIFT_N(VQSHRNT_S, vqshrnt_s)
+DO_2SHIFT_N(VQSHRNB_U, vqshrnb_u)
+DO_2SHIFT_N(VQSHRNT_U, vqshrnt_u)
+DO_2SHIFT_N(VQSHRUNB, vqshrunb)
+DO_2SHIFT_N(VQSHRUNT, vqshrunt)
+DO_2SHIFT_N(VQRSHRNB_S, vqrshrnb_s)
+DO_2SHIFT_N(VQRSHRNT_S, vqrshrnt_s)
+DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u)
+DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u)
+DO_2SHIFT_N(VQRSHRUNB, vqrshrunb)
+DO_2SHIFT_N(VQRSHRUNT, vqrshrunt)
--
2.20.1
- [PATCH 08/18] target/arm: Implement MVE vector shift right by immediate insns, (continued)
- [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, 2021/06/28
- [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 <=
- [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
[PATCH 11/18] target/arm: Implement MVE VSHRN, VRSHRN, Peter Maydell, 2021/06/28