[v6,29/61] target/riscv: vector narrowing fixed-point clip instructions

Commit Message

LIU Zhiwei March 17, 2020, 3:06 p.m. UTC

Signed-off-by: LIU Zhiwei <[e-mail]>
---
 target/riscv/helper.h                   |  13 +++
 target/riscv/insn32.decode              |   6 ++
 target/riscv/insn_trans/trans_rvv.inc.c |   8 ++
 target/riscv/vector_helper.c            | 137 ++++++++++++++++++++++++
 4 files changed, 164 insertions(+)

Comments

Richard Henderson March 28, 2020, 1:50 a.m. UTC | #1

On 3/17/20 8:06 AM, LIU Zhiwei wrote:
> Signed-off-by: LIU Zhiwei <[e-mail]>
> ---
>  target/riscv/helper.h                   |  13 +++
>  target/riscv/insn32.decode              |   6 ++
>  target/riscv/insn_trans/trans_rvv.inc.c |   8 ++
>  target/riscv/vector_helper.c            | 137 ++++++++++++++++++++++++
>  4 files changed, 164 insertions(+)

Reviewed-by: Richard Henderson <[e-mail]>


r~

Patch

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index ce90e5ce0d..aba0c32cde 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -780,3 +780,16 @@  DEF_HELPER_6(vssra_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vssra_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vssra_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vssra_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vnclip_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclip_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 2ecac3d96d..8b898f9bad 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -437,6 +437,12 @@  vssrl_vi        101010 . ..... ..... 011 ..... 1010111 @r_vm
 vssra_vv        101011 . ..... ..... 000 ..... 1010111 @r_vm
 vssra_vx        101011 . ..... ..... 100 ..... 1010111 @r_vm
 vssra_vi        101011 . ..... ..... 011 ..... 1010111 @r_vm
+vnclipu_vv      101110 . ..... ..... 000 ..... 1010111 @r_vm
+vnclipu_vx      101110 . ..... ..... 100 ..... 1010111 @r_vm
+vnclipu_vi      101110 . ..... ..... 011 ..... 1010111 @r_vm
+vnclip_vv       101111 . ..... ..... 000 ..... 1010111 @r_vm
+vnclip_vx       101111 . ..... ..... 100 ..... 1010111 @r_vm
+vnclip_vi       101111 . ..... ..... 011 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 684104a978..ccf6421757 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1664,3 +1664,11 @@  GEN_OPIVX_TRANS(vssrl_vx,  opivx_check)
 GEN_OPIVX_TRANS(vssra_vx,  opivx_check)
 GEN_OPIVI_TRANS(vssrl_vi, 1, vssrl_vx, opivx_check)
 GEN_OPIVI_TRANS(vssra_vi, 0, vssra_vx, opivx_check)
+
+/* Vector Narrowing Fixed-Point Clip Instructions */
+GEN_OPIVV_NARROW_TRANS(vnclipu_vv)
+GEN_OPIVV_NARROW_TRANS(vnclip_vv)
+GEN_OPIVX_NARROW_TRANS(vnclipu_vx)
+GEN_OPIVX_NARROW_TRANS(vnclip_vx)
+GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx)
+GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index f50312f724..f4dc6c4783 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -868,6 +868,12 @@  GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl)
 #define WOP_SSU_B int16_t, int8_t, uint8_t, int16_t, uint16_t
 #define WOP_SSU_H int32_t, int16_t, uint16_t, int32_t, uint32_t
 #define WOP_SSU_W int64_t, int32_t, uint32_t, int64_t, uint64_t
+#define NOP_SSS_B int8_t, int8_t, int16_t, int8_t, int16_t
+#define NOP_SSS_H int16_t, int16_t, int32_t, int16_t, int32_t
+#define NOP_SSS_W int32_t, int32_t, int64_t, int32_t, int64_t
+#define NOP_UUU_B uint8_t, uint8_t, uint16_t, uint8_t, uint16_t
+#define NOP_UUU_H uint16_t, uint16_t, uint32_t, uint16_t, uint32_t
+#define NOP_UUU_W uint32_t, uint32_t, uint64_t, uint32_t, uint64_t
 
 /* operation of two vector elements */
 typedef void opivv2_fn(void *vd, void *vs1, void *vs2, int i);
@@ -2997,6 +3003,7 @@  vssra64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
     res   = (a >> shift)  + round;
     return res;
 }
+
 RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
 RVVCALL(OPIVV2_RM, vssra_vv_h, OP_SSS_H, H2, H2, H2, vssra16)
 RVVCALL(OPIVV2_RM, vssra_vv_w, OP_SSS_W, H4, H4, H4, vssra32)
@@ -3014,3 +3021,133 @@  GEN_VEXT_VX_RM(vssra_vx_b, 1, 1, clearb)
 GEN_VEXT_VX_RM(vssra_vx_h, 2, 2, clearh)
 GEN_VEXT_VX_RM(vssra_vx_w, 4, 4, clearl)
 GEN_VEXT_VX_RM(vssra_vx_d, 8, 8, clearq)
+
+/* Vector Narrowing Fixed-Point Clip Instructions */
+static inline int8_t
+vnclip8(CPURISCVState *env, int vxrm, int16_t a, int8_t b)
+{
+    uint8_t round, shift = b & 0xf;
+    int16_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    if (res > INT8_MAX) {
+        env->vxsat = 0x1;
+        return INT8_MAX;
+    } else if (res < INT8_MIN) {
+        env->vxsat = 0x1;
+        return INT8_MIN;
+    } else {
+        return res;
+    }
+}
+static inline int16_t
+vnclip16(CPURISCVState *env, int vxrm, int32_t a, int16_t b)
+{
+    uint8_t round, shift = b & 0x1f;
+    int32_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    if (res > INT16_MAX) {
+        env->vxsat = 0x1;
+        return INT16_MAX;
+    } else if (res < INT16_MIN) {
+        env->vxsat = 0x1;
+        return INT16_MIN;
+    } else {
+        return res;
+    }
+}
+static inline int32_t
+vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
+{
+    uint8_t round, shift = b & 0x3f;
+    int64_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    if (res > INT32_MAX) {
+        env->vxsat = 0x1;
+        return INT32_MAX;
+    } else if (res < INT32_MIN) {
+        env->vxsat = 0x1;
+        return INT32_MIN;
+    } else {
+        return res;
+    }
+}
+
+RVVCALL(OPIVV2_RM, vnclip_vv_b, NOP_SSS_B, H1, H2, H1, vnclip8)
+RVVCALL(OPIVV2_RM, vnclip_vv_h, NOP_SSS_H, H2, H4, H2, vnclip16)
+RVVCALL(OPIVV2_RM, vnclip_vv_w, NOP_SSS_W, H4, H8, H4, vnclip32)
+GEN_VEXT_VV_RM(vnclip_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vnclip_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vnclip_vv_w, 4, 4, clearl)
+
+RVVCALL(OPIVX2_RM, vnclip_vx_b, NOP_SSS_B, H1, H2, vnclip8)
+RVVCALL(OPIVX2_RM, vnclip_vx_h, NOP_SSS_H, H2, H4, vnclip16)
+RVVCALL(OPIVX2_RM, vnclip_vx_w, NOP_SSS_W, H4, H8, vnclip32)
+GEN_VEXT_VX_RM(vnclip_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vnclip_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vnclip_vx_w, 4, 4, clearl)
+
+static inline uint8_t
+vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
+{
+    uint8_t round, shift = b & 0xf;
+    uint16_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    if (res > UINT8_MAX) {
+        env->vxsat = 0x1;
+        return UINT8_MAX;
+    } else {
+        return res;
+    }
+}
+static inline uint16_t
+vnclipu16(CPURISCVState *env, int vxrm, uint32_t a, uint16_t b)
+{
+    uint8_t round, shift = b & 0x1f;
+    uint32_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    if (res > UINT16_MAX) {
+        env->vxsat = 0x1;
+        return UINT16_MAX;
+    } else {
+        return res;
+    }
+}
+static inline uint32_t
+vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
+{
+    uint8_t round, shift = b & 0x3f;
+    int64_t res;
+
+    round = get_round(vxrm, a, shift);
+    res   = (a >> shift)  + round;
+    if (res > UINT32_MAX) {
+        env->vxsat = 0x1;
+        return UINT32_MAX;
+    } else {
+        return res;
+    }
+}
+
+RVVCALL(OPIVV2_RM, vnclipu_vv_b, NOP_UUU_B, H1, H2, H1, vnclipu8)
+RVVCALL(OPIVV2_RM, vnclipu_vv_h, NOP_UUU_H, H2, H4, H2, vnclipu16)
+RVVCALL(OPIVV2_RM, vnclipu_vv_w, NOP_UUU_W, H4, H8, H4, vnclipu32)
+GEN_VEXT_VV_RM(vnclipu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vnclipu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vnclipu_vv_w, 4, 4, clearl)
+
+RVVCALL(OPIVX2_RM, vnclipu_vx_b, NOP_UUU_B, H1, H2, vnclipu8)
+RVVCALL(OPIVX2_RM, vnclipu_vx_h, NOP_UUU_H, H2, H4, vnclipu16)
+RVVCALL(OPIVX2_RM, vnclipu_vx_w, NOP_UUU_W, H4, H8, vnclipu32)
+GEN_VEXT_VX_RM(vnclipu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vnclipu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vnclipu_vx_w, 4, 4, clearl)