target/loongarch: Implement xvfrstp

This patch includes:
- XVFRSTP[I].{B/H}.

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230914022645.1151356-46-gaosong@loongson.cn>

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 7f04c912aa9ad46c014c468cf31b647c049cea84..1c4aecaa935cc5ff3e72a1f6ec7601c37c7b0a4a 100644 (file)
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -2235,6 +2235,11 @@ INSN_LASX(xvbitrevi_h,       vv_i)
 INSN_LASX(xvbitrevi_w,       vv_i)
 INSN_LASX(xvbitrevi_d,       vv_i)
 
+INSN_LASX(xvfrstp_b,         vvv)
+INSN_LASX(xvfrstp_h,         vvv)
+INSN_LASX(xvfrstpi_b,        vv_i)
+INSN_LASX(xvfrstpi_h,        vv_i)
+
 INSN_LASX(xvreplgr2vr_b,     vr)
 INSN_LASX(xvreplgr2vr_h,     vr)
 INSN_LASX(xvreplgr2vr_w,     vr)

diff --git a/target/loongarch/insn_trans/trans_vec.c.inc b/target/loongarch/insn_trans/trans_vec.c.inc
index 9e7eb303562f7c91b1f7b63ed368520a86ea2e6e..c1e7130a73fab9fc12b4d37b35e929b3867421c6 100644 (file)
--- a/target/loongarch/insn_trans/trans_vec.c.inc
+++ b/target/loongarch/insn_trans/trans_vec.c.inc
@@ -4300,6 +4300,10 @@ TRANS(vfrstp_b, LSX, gen_vvv, gen_helper_vfrstp_b)
 TRANS(vfrstp_h, LSX, gen_vvv, gen_helper_vfrstp_h)
 TRANS(vfrstpi_b, LSX, gen_vv_i, gen_helper_vfrstpi_b)
 TRANS(vfrstpi_h, LSX, gen_vv_i, gen_helper_vfrstpi_h)
+TRANS(xvfrstp_b, LASX, gen_xxx, gen_helper_vfrstp_b)
+TRANS(xvfrstp_h, LASX, gen_xxx, gen_helper_vfrstp_h)
+TRANS(xvfrstpi_b, LASX, gen_xx_i, gen_helper_vfrstpi_b)
+TRANS(xvfrstpi_h, LASX, gen_xx_i, gen_helper_vfrstpi_h)
 
 TRANS(vfadd_s, LSX, gen_vvv_ptr, gen_helper_vfadd_s)
 TRANS(vfadd_d, LSX, gen_vvv_ptr, gen_helper_vfadd_d)

diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index cb6db8002aeb1bce5056ddbd3d8399c4812de7ae..6035fe139c94015668a22930e6646f9f6d809faa 100644 (file)
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1811,6 +1811,11 @@ xvbitrevi_h      0111 01110001 10000 1 .... ..... .....   @vv_ui4
 xvbitrevi_w      0111 01110001 10001 ..... ..... .....    @vv_ui5
 xvbitrevi_d      0111 01110001 1001 ...... ..... .....    @vv_ui6
 
+xvfrstp_b        0111 01010010 10110 ..... ..... .....    @vvv
+xvfrstp_h        0111 01010010 10111 ..... ..... .....    @vvv
+xvfrstpi_b       0111 01101001 10100 ..... ..... .....    @vv_ui5
+xvfrstpi_h       0111 01101001 10101 ..... ..... .....    @vv_ui5
+
 xvreplgr2vr_b    0111 01101001 11110 00000 ..... .....    @vr
 xvreplgr2vr_h    0111 01101001 11110 00001 ..... .....    @vr
 xvreplgr2vr_w    0111 01101001 11110 00010 ..... .....    @vr

diff --git a/target/loongarch/vec_helper.c b/target/loongarch/vec_helper.c
index ec63efb428e4968e8ecd69fa876d44db4f13c613..9ddbbc665adb9dbb5d0143d7346c2fa082ea373e 100644 (file)
--- a/target/loongarch/vec_helper.c
+++ b/target/loongarch/vec_helper.c
@@ -2369,18 +2369,22 @@ DO_BITI(vbitrevi_d, 64, UD, DO_BITREV)
 #define VFRSTP(NAME, BIT, MASK, E)                             \
 void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t desc) \
 {                                                              \
-    int i, m;                                                  \
+    int i, j, m, ofs;                                          \
     VReg *Vd = (VReg *)vd;                                     \
     VReg *Vj = (VReg *)vj;                                     \
     VReg *Vk = (VReg *)vk;                                     \
+    int oprsz = simd_oprsz(desc);                              \
                                                                \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                        \
-        if (Vj->E(i) < 0) {                                    \
-            break;                                             \
+    ofs = LSX_LEN / BIT;                                       \
+    for (i = 0; i < oprsz / 16; i++) {                         \
+        m = Vk->E(i * ofs) & MASK;                             \
+        for (j = 0; j < ofs; j++) {                            \
+            if (Vj->E(j + ofs * i) < 0) {                      \
+                break;                                         \
+            }                                                  \
         }                                                      \
+        Vd->E(m + i * ofs) = j;                                \
     }                                                          \
-    m = Vk->E(0) & MASK;                                       \
-    Vd->E(m) = i;                                              \
 }
 
 VFRSTP(vfrstp_b, 8, 0xf, B)
@@ -2389,17 +2393,21 @@ VFRSTP(vfrstp_h, 16, 0x7, H)
 #define VFRSTPI(NAME, BIT, E)                                      \
 void HELPER(NAME)(void *vd, void *vj, uint64_t imm, uint32_t desc) \
 {                                                                  \
-    int i, m;                                                      \
+    int i, j, m, ofs;                                              \
     VReg *Vd = (VReg *)vd;                                         \
     VReg *Vj = (VReg *)vj;                                         \
+    int oprsz = simd_oprsz(desc);                                  \
                                                                    \
-    for (i = 0; i < LSX_LEN/BIT; i++) {                            \
-        if (Vj->E(i) < 0) {                                        \
-            break;                                                 \
+    ofs = LSX_LEN / BIT;                                           \
+    m = imm % ofs;                                                 \
+    for (i = 0; i < oprsz / 16; i++) {                             \
+        for (j = 0; j < ofs; j++) {                                \
+            if (Vj->E(j + ofs * i) < 0) {                          \
+                break;                                             \
+            }                                                      \
         }                                                          \
+        Vd->E(m + i * ofs) = j;                                    \
     }                                                              \
-    m = imm % (LSX_LEN/BIT);                                       \
-    Vd->E(m) = i;                                                  \
 }
 
 VFRSTPI(vfrstpi_b, 8,  B)