summaryrefslogtreecommitdiffstats
path: root/target/arm/neon_helper.c
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm/neon_helper.c')
-rw-r--r--target/arm/neon_helper.c162
1 files changed, 88 insertions, 74 deletions
diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c
index ebdf7c9b10..689491cad3 100644
--- a/target/arm/neon_helper.c
+++ b/target/arm/neon_helper.c
@@ -2027,12 +2027,12 @@ uint64_t HELPER(neon_acgt_f64)(uint64_t a, uint64_t b, void *fpstp)
#define ELEM(V, N, SIZE) (((V) >> ((N) * (SIZE))) & ((1ull << (SIZE)) - 1))
-void HELPER(neon_qunzip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_qunzip8)(void *vd, void *vm)
{
- uint64_t zm0 = float64_val(env->vfp.regs[rm]);
- uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
- uint64_t zd0 = float64_val(env->vfp.regs[rd]);
- uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd0 = rd[0], zd1 = rd[1];
+ uint64_t zm0 = rm[0], zm1 = rm[1];
+
uint64_t d0 = ELEM(zd0, 0, 8) | (ELEM(zd0, 2, 8) << 8)
| (ELEM(zd0, 4, 8) << 16) | (ELEM(zd0, 6, 8) << 24)
| (ELEM(zd1, 0, 8) << 32) | (ELEM(zd1, 2, 8) << 40)
@@ -2049,18 +2049,19 @@ void HELPER(neon_qunzip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
| (ELEM(zm0, 5, 8) << 16) | (ELEM(zm0, 7, 8) << 24)
| (ELEM(zm1, 1, 8) << 32) | (ELEM(zm1, 3, 8) << 40)
| (ELEM(zm1, 5, 8) << 48) | (ELEM(zm1, 7, 8) << 56);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rm + 1] = make_float64(m1);
- env->vfp.regs[rd] = make_float64(d0);
- env->vfp.regs[rd + 1] = make_float64(d1);
+
+ rm[0] = m0;
+ rm[1] = m1;
+ rd[0] = d0;
+ rd[1] = d1;
}
-void HELPER(neon_qunzip16)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_qunzip16)(void *vd, void *vm)
{
- uint64_t zm0 = float64_val(env->vfp.regs[rm]);
- uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
- uint64_t zd0 = float64_val(env->vfp.regs[rd]);
- uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd0 = rd[0], zd1 = rd[1];
+ uint64_t zm0 = rm[0], zm1 = rm[1];
+
uint64_t d0 = ELEM(zd0, 0, 16) | (ELEM(zd0, 2, 16) << 16)
| (ELEM(zd1, 0, 16) << 32) | (ELEM(zd1, 2, 16) << 48);
uint64_t d1 = ELEM(zm0, 0, 16) | (ELEM(zm0, 2, 16) << 16)
@@ -2069,32 +2070,35 @@ void HELPER(neon_qunzip16)(CPUARMState *env, uint32_t rd, uint32_t rm)
| (ELEM(zd1, 1, 16) << 32) | (ELEM(zd1, 3, 16) << 48);
uint64_t m1 = ELEM(zm0, 1, 16) | (ELEM(zm0, 3, 16) << 16)
| (ELEM(zm1, 1, 16) << 32) | (ELEM(zm1, 3, 16) << 48);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rm + 1] = make_float64(m1);
- env->vfp.regs[rd] = make_float64(d0);
- env->vfp.regs[rd + 1] = make_float64(d1);
+
+ rm[0] = m0;
+ rm[1] = m1;
+ rd[0] = d0;
+ rd[1] = d1;
}
-void HELPER(neon_qunzip32)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_qunzip32)(void *vd, void *vm)
{
- uint64_t zm0 = float64_val(env->vfp.regs[rm]);
- uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
- uint64_t zd0 = float64_val(env->vfp.regs[rd]);
- uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd0 = rd[0], zd1 = rd[1];
+ uint64_t zm0 = rm[0], zm1 = rm[1];
+
uint64_t d0 = ELEM(zd0, 0, 32) | (ELEM(zd1, 0, 32) << 32);
uint64_t d1 = ELEM(zm0, 0, 32) | (ELEM(zm1, 0, 32) << 32);
uint64_t m0 = ELEM(zd0, 1, 32) | (ELEM(zd1, 1, 32) << 32);
uint64_t m1 = ELEM(zm0, 1, 32) | (ELEM(zm1, 1, 32) << 32);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rm + 1] = make_float64(m1);
- env->vfp.regs[rd] = make_float64(d0);
- env->vfp.regs[rd + 1] = make_float64(d1);
+
+ rm[0] = m0;
+ rm[1] = m1;
+ rd[0] = d0;
+ rd[1] = d1;
}
-void HELPER(neon_unzip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_unzip8)(void *vd, void *vm)
{
- uint64_t zm = float64_val(env->vfp.regs[rm]);
- uint64_t zd = float64_val(env->vfp.regs[rd]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd = rd[0], zm = rm[0];
+
uint64_t d0 = ELEM(zd, 0, 8) | (ELEM(zd, 2, 8) << 8)
| (ELEM(zd, 4, 8) << 16) | (ELEM(zd, 6, 8) << 24)
| (ELEM(zm, 0, 8) << 32) | (ELEM(zm, 2, 8) << 40)
@@ -2103,28 +2107,31 @@ void HELPER(neon_unzip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
| (ELEM(zd, 5, 8) << 16) | (ELEM(zd, 7, 8) << 24)
| (ELEM(zm, 1, 8) << 32) | (ELEM(zm, 3, 8) << 40)
| (ELEM(zm, 5, 8) << 48) | (ELEM(zm, 7, 8) << 56);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rd] = make_float64(d0);
+
+ rm[0] = m0;
+ rd[0] = d0;
}
-void HELPER(neon_unzip16)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_unzip16)(void *vd, void *vm)
{
- uint64_t zm = float64_val(env->vfp.regs[rm]);
- uint64_t zd = float64_val(env->vfp.regs[rd]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd = rd[0], zm = rm[0];
+
uint64_t d0 = ELEM(zd, 0, 16) | (ELEM(zd, 2, 16) << 16)
| (ELEM(zm, 0, 16) << 32) | (ELEM(zm, 2, 16) << 48);
uint64_t m0 = ELEM(zd, 1, 16) | (ELEM(zd, 3, 16) << 16)
| (ELEM(zm, 1, 16) << 32) | (ELEM(zm, 3, 16) << 48);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rd] = make_float64(d0);
+
+ rm[0] = m0;
+ rd[0] = d0;
}
-void HELPER(neon_qzip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_qzip8)(void *vd, void *vm)
{
- uint64_t zm0 = float64_val(env->vfp.regs[rm]);
- uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
- uint64_t zd0 = float64_val(env->vfp.regs[rd]);
- uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd0 = rd[0], zd1 = rd[1];
+ uint64_t zm0 = rm[0], zm1 = rm[1];
+
uint64_t d0 = ELEM(zd0, 0, 8) | (ELEM(zm0, 0, 8) << 8)
| (ELEM(zd0, 1, 8) << 16) | (ELEM(zm0, 1, 8) << 24)
| (ELEM(zd0, 2, 8) << 32) | (ELEM(zm0, 2, 8) << 40)
@@ -2141,18 +2148,19 @@ void HELPER(neon_qzip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
| (ELEM(zd1, 5, 8) << 16) | (ELEM(zm1, 5, 8) << 24)
| (ELEM(zd1, 6, 8) << 32) | (ELEM(zm1, 6, 8) << 40)
| (ELEM(zd1, 7, 8) << 48) | (ELEM(zm1, 7, 8) << 56);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rm + 1] = make_float64(m1);
- env->vfp.regs[rd] = make_float64(d0);
- env->vfp.regs[rd + 1] = make_float64(d1);
+
+ rm[0] = m0;
+ rm[1] = m1;
+ rd[0] = d0;
+ rd[1] = d1;
}
-void HELPER(neon_qzip16)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_qzip16)(void *vd, void *vm)
{
- uint64_t zm0 = float64_val(env->vfp.regs[rm]);
- uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
- uint64_t zd0 = float64_val(env->vfp.regs[rd]);
- uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd0 = rd[0], zd1 = rd[1];
+ uint64_t zm0 = rm[0], zm1 = rm[1];
+
uint64_t d0 = ELEM(zd0, 0, 16) | (ELEM(zm0, 0, 16) << 16)
| (ELEM(zd0, 1, 16) << 32) | (ELEM(zm0, 1, 16) << 48);
uint64_t d1 = ELEM(zd0, 2, 16) | (ELEM(zm0, 2, 16) << 16)
@@ -2161,32 +2169,35 @@ void HELPER(neon_qzip16)(CPUARMState *env, uint32_t rd, uint32_t rm)
| (ELEM(zd1, 1, 16) << 32) | (ELEM(zm1, 1, 16) << 48);
uint64_t m1 = ELEM(zd1, 2, 16) | (ELEM(zm1, 2, 16) << 16)
| (ELEM(zd1, 3, 16) << 32) | (ELEM(zm1, 3, 16) << 48);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rm + 1] = make_float64(m1);
- env->vfp.regs[rd] = make_float64(d0);
- env->vfp.regs[rd + 1] = make_float64(d1);
+
+ rm[0] = m0;
+ rm[1] = m1;
+ rd[0] = d0;
+ rd[1] = d1;
}
-void HELPER(neon_qzip32)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_qzip32)(void *vd, void *vm)
{
- uint64_t zm0 = float64_val(env->vfp.regs[rm]);
- uint64_t zm1 = float64_val(env->vfp.regs[rm + 1]);
- uint64_t zd0 = float64_val(env->vfp.regs[rd]);
- uint64_t zd1 = float64_val(env->vfp.regs[rd + 1]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd0 = rd[0], zd1 = rd[1];
+ uint64_t zm0 = rm[0], zm1 = rm[1];
+
uint64_t d0 = ELEM(zd0, 0, 32) | (ELEM(zm0, 0, 32) << 32);
uint64_t d1 = ELEM(zd0, 1, 32) | (ELEM(zm0, 1, 32) << 32);
uint64_t m0 = ELEM(zd1, 0, 32) | (ELEM(zm1, 0, 32) << 32);
uint64_t m1 = ELEM(zd1, 1, 32) | (ELEM(zm1, 1, 32) << 32);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rm + 1] = make_float64(m1);
- env->vfp.regs[rd] = make_float64(d0);
- env->vfp.regs[rd + 1] = make_float64(d1);
+
+ rm[0] = m0;
+ rm[1] = m1;
+ rd[0] = d0;
+ rd[1] = d1;
}
-void HELPER(neon_zip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_zip8)(void *vd, void *vm)
{
- uint64_t zm = float64_val(env->vfp.regs[rm]);
- uint64_t zd = float64_val(env->vfp.regs[rd]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd = rd[0], zm = rm[0];
+
uint64_t d0 = ELEM(zd, 0, 8) | (ELEM(zm, 0, 8) << 8)
| (ELEM(zd, 1, 8) << 16) | (ELEM(zm, 1, 8) << 24)
| (ELEM(zd, 2, 8) << 32) | (ELEM(zm, 2, 8) << 40)
@@ -2195,20 +2206,23 @@ void HELPER(neon_zip8)(CPUARMState *env, uint32_t rd, uint32_t rm)
| (ELEM(zd, 5, 8) << 16) | (ELEM(zm, 5, 8) << 24)
| (ELEM(zd, 6, 8) << 32) | (ELEM(zm, 6, 8) << 40)
| (ELEM(zd, 7, 8) << 48) | (ELEM(zm, 7, 8) << 56);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rd] = make_float64(d0);
+
+ rm[0] = m0;
+ rd[0] = d0;
}
-void HELPER(neon_zip16)(CPUARMState *env, uint32_t rd, uint32_t rm)
+void HELPER(neon_zip16)(void *vd, void *vm)
{
- uint64_t zm = float64_val(env->vfp.regs[rm]);
- uint64_t zd = float64_val(env->vfp.regs[rd]);
+ uint64_t *rd = vd, *rm = vm;
+ uint64_t zd = rd[0], zm = rm[0];
+
uint64_t d0 = ELEM(zd, 0, 16) | (ELEM(zm, 0, 16) << 16)
| (ELEM(zd, 1, 16) << 32) | (ELEM(zm, 1, 16) << 48);
uint64_t m0 = ELEM(zd, 2, 16) | (ELEM(zm, 2, 16) << 16)
| (ELEM(zd, 3, 16) << 32) | (ELEM(zm, 3, 16) << 48);
- env->vfp.regs[rm] = make_float64(m0);
- env->vfp.regs[rd] = make_float64(d0);
+
+ rm[0] = m0;
+ rd[0] = d0;
}
/* Helper function for 64 bit polynomial multiply case:
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2025-04-29 08:54:42 +0200