[Qemu-devel] [PATCH 12/38] tcg: Add gvec expanders for variable shift

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 accel/tcg/tcg-runtime.h      |  15 ++++
 tcg/tcg-op-gvec.h            |   7 ++
 tcg/tcg-op.h                 |   4 ++
 accel/tcg/tcg-runtime-gvec.c | 132 +++++++++++++++++++++++++++++++++++
 tcg/tcg-op-gvec.c            |  87 +++++++++++++++++++++++
 tcg/tcg-op-vec.c             |  15 ++++
 6 files changed, 260 insertions(+)

diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h
index dfe325625c..ed3ce5fd91 100644
--- a/accel/tcg/tcg-runtime.h
+++ b/accel/tcg/tcg-runtime.h
@@ -254,6 +254,21 @@ DEF_HELPER_FLAGS_3(gvec_sar16i, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(gvec_sar32i, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(gvec_sar64i, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(gvec_shl8v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_shl16v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_shl32v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_shl64v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_shr8v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_shr16v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_shr32v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_shr64v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(gvec_sar8v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sar16v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sar32v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sar64v, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(gvec_eq8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_eq16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_eq32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h
index 850da32ded..1cd18a959a 100644
--- a/tcg/tcg-op-gvec.h
+++ b/tcg/tcg-op-gvec.h
@@ -294,6 +294,13 @@ void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,
 void tcg_gen_gvec_sari(unsigned vece, uint32_t dofs, uint32_t aofs,
                        int64_t shift, uint32_t oprsz, uint32_t maxsz);
 
+void tcg_gen_gvec_shlv(unsigned vece, uint32_t dofs, uint32_t aofs,
+                       uint32_t bofs, uint32_t oprsz, uint32_t maxsz);
+void tcg_gen_gvec_shrv(unsigned vece, uint32_t dofs, uint32_t aofs,
+                       uint32_t bofs, uint32_t oprsz, uint32_t maxsz);
+void tcg_gen_gvec_sarv(unsigned vece, uint32_t dofs, uint32_t aofs,
+                       uint32_t bofs, uint32_t oprsz, uint32_t maxsz);
+
 void tcg_gen_gvec_cmp(TCGCond cond, unsigned vece, uint32_t dofs,
                       uint32_t aofs, uint32_t bofs,
                       uint32_t oprsz, uint32_t maxsz);
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 9fff9864f6..833c6330b5 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -986,6 +986,10 @@ void tcg_gen_shli_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i);
 void tcg_gen_shri_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i);
 void tcg_gen_sari_vec(unsigned vece, TCGv_vec r, TCGv_vec a, int64_t i);
 
+void tcg_gen_shlv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s);
+void tcg_gen_shrv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s);
+void tcg_gen_sarv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec s);
+
 void tcg_gen_cmp_vec(TCGCond cond, unsigned vece, TCGv_vec r,
                      TCGv_vec a, TCGv_vec b);
 
diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c
index e2c6f24262..7b88f5590c 100644
--- a/accel/tcg/tcg-runtime-gvec.c
+++ b/accel/tcg/tcg-runtime-gvec.c
@@ -725,6 +725,138 @@ void HELPER(gvec_sar64i)(void *d, void *a, uint32_t desc)
     clear_high(d, oprsz, desc);
 }
 
+void HELPER(gvec_shl8v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) << *(uint8_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_shl16v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) << *(uint16_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_shl32v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) << *(uint32_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_shl64v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) << *(uint64_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_shr8v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint8_t)) {
+        *(uint8_t *)(d + i) = *(uint8_t *)(a + i) >> *(uint8_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_shr16v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint16_t)) {
+        *(uint16_t *)(d + i) = *(uint16_t *)(a + i) >> *(uint16_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_shr32v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint32_t)) {
+        *(uint32_t *)(d + i) = *(uint32_t *)(a + i) >> *(uint32_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_shr64v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) >> *(uint64_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_sar8v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(vec8)) {
+        *(int8_t *)(d + i) = *(int8_t *)(a + i) >> *(int8_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_sar16v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(int16_t)) {
+        *(int16_t *)(d + i) = *(int16_t *)(a + i) >> *(int16_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_sar32v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(vec32)) {
+        *(int32_t *)(d + i) = *(int32_t *)(a + i) >> *(int32_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
+void HELPER(gvec_sar64v)(void *d, void *a, void *b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {
+        *(int64_t *)(d + i) = *(int64_t *)(a + i) >> *(int64_t *)(b + i);
+    }
+    clear_high(d, oprsz, desc);
+}
+
 /* If vectors are enabled, the compiler fills in -1 for true.
    Otherwise, we must take care of this by hand.  */
 #ifdef CONFIG_VECTOR16
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index f056018713..5d28184045 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -2382,6 +2382,93 @@ void tcg_gen_gvec_sari(unsigned vece, uint32_t dofs, uint32_t aofs,
     }
 }
 
+void tcg_gen_gvec_shlv(unsigned vece, uint32_t dofs, uint32_t aofs,
+                       uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen3 g[4] = {
+        { .fniv = tcg_gen_shlv_vec,
+          .fno = gen_helper_gvec_shl8v,
+          .opc = INDEX_op_shlv_vec,
+          .vece = MO_8 },
+        { .fniv = tcg_gen_shlv_vec,
+          .fno = gen_helper_gvec_shl16v,
+          .opc = INDEX_op_shlv_vec,
+          .vece = MO_16 },
+        { .fni4 = tcg_gen_shl_i32,
+          .fniv = tcg_gen_shlv_vec,
+          .fno = gen_helper_gvec_shl32v,
+          .opc = INDEX_op_shlv_vec,
+          .vece = MO_32 },
+        { .fni8 = tcg_gen_shl_i64,
+          .fniv = tcg_gen_shlv_vec,
+          .fno = gen_helper_gvec_shl64v,
+          .opc = INDEX_op_shlv_vec,
+          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+          .vece = MO_64 },
+    };
+
+    tcg_debug_assert(vece <= MO_64);
+    tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
+}
+
+void tcg_gen_gvec_shrv(unsigned vece, uint32_t dofs, uint32_t aofs,
+                       uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen3 g[4] = {
+        { .fniv = tcg_gen_shrv_vec,
+          .fno = gen_helper_gvec_shr8v,
+          .opc = INDEX_op_shrv_vec,
+          .vece = MO_8 },
+        { .fniv = tcg_gen_shrv_vec,
+          .fno = gen_helper_gvec_shr16v,
+          .opc = INDEX_op_shrv_vec,
+          .vece = MO_16 },
+        { .fni4 = tcg_gen_shr_i32,
+          .fniv = tcg_gen_shrv_vec,
+          .fno = gen_helper_gvec_shr32v,
+          .opc = INDEX_op_shrv_vec,
+          .vece = MO_32 },
+        { .fni8 = tcg_gen_shr_i64,
+          .fniv = tcg_gen_shrv_vec,
+          .fno = gen_helper_gvec_shr64v,
+          .opc = INDEX_op_shrv_vec,
+          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+          .vece = MO_64 },
+    };
+
+    tcg_debug_assert(vece <= MO_64);
+    tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
+}
+
+void tcg_gen_gvec_sarv(unsigned vece, uint32_t dofs, uint32_t aofs,
+                       uint32_t bofs, uint32_t oprsz, uint32_t maxsz)
+{
+    static const GVecGen3 g[4] = {
+        { .fniv = tcg_gen_sarv_vec,
+          .fno = gen_helper_gvec_sar8v,
+          .opc = INDEX_op_sarv_vec,
+          .vece = MO_8 },
+        { .fniv = tcg_gen_sarv_vec,
+          .fno = gen_helper_gvec_sar16v,
+          .opc = INDEX_op_sarv_vec,
+          .vece = MO_16 },
+        { .fni4 = tcg_gen_sar_i32,
+          .fniv = tcg_gen_sarv_vec,
+          .fno = gen_helper_gvec_sar32v,
+          .opc = INDEX_op_sarv_vec,
+          .vece = MO_32 },
+        { .fni8 = tcg_gen_sar_i64,
+          .fniv = tcg_gen_sarv_vec,
+          .fno = gen_helper_gvec_sar64v,
+          .opc = INDEX_op_sarv_vec,
+          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+          .vece = MO_64 },
+    };
+
+    tcg_debug_assert(vece <= MO_64);
+    tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]);
+}
+
 /* Expand OPSZ bytes worth of three-operand operations using i32 elements.  */
 static void expand_cmp_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs,
                            uint32_t oprsz, TCGCond cond)
diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c
index ce7987b858..6601cb8a8f 100644
--- a/tcg/tcg-op-vec.c
+++ b/tcg/tcg-op-vec.c
@@ -481,3 +481,18 @@ void tcg_gen_umax_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
 {
     do_op3(vece, r, a, b, INDEX_op_umax_vec);
 }
+
+void tcg_gen_shlv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
+{
+    do_op3(vece, r, a, b, INDEX_op_shlv_vec);
+}
+
+void tcg_gen_shrv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
+{
+    do_op3(vece, r, a, b, INDEX_op_shrv_vec);
+}
+
+void tcg_gen_sarv_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
+{
+    do_op3(vece, r, a, b, INDEX_op_sarv_vec);
+}
-- 
2.17.1