Hi,
The signed variants of the qtbl and qtbx intrinsics currently
take an int8x<8,16> for their control vector parameter.
This should be a uint8x<8,16> parameter.
Fixed as attached and checked against aarch64.exp on aarch64-none-elf
with no regressions.
Is this OK to commit?
I have some similair patches kicking around in my tree, these feel
obvious, but I'd like to check that others' share that perspective
before I go committing anything!
Thanks,
James
---
gcc/
2013-09-06 James Greenhalgh <james.greenha...@arm.com>
* config/aarch64/arm_neon.h
(vqtbl<1,2,3,4><q>_s8): Fix control vector parameter type.
(vqtbx<1,2,3,4><q>_s8): Likewise.
gcc/testsuite/
2013-09-06 James Greenhalgh <james.greenha...@arm.com>
* gcc.target/aarch64/table-intrinsics.c
(qtbl_tests8_< ,2,3,4>): Fix control vector parameter type.
(qtb_tests8_< ,2,3,4>): Likewise.
(qtblq_tests8_< ,2,3,4>): Likewise.
(qtbxq_tests8_< ,2,3,4>): Likewise.
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index e20d34e..5864f2c 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -15973,7 +15973,7 @@ vqtbl1_p8 (poly8x16_t a, uint8x8_t b)
}
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbl1_s8 (int8x16_t a, int8x8_t b)
+vqtbl1_s8 (int8x16_t a, uint8x8_t b)
{
int8x8_t result;
__asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
@@ -16006,7 +16006,7 @@ vqtbl1q_p8 (poly8x16_t a, uint8x16_t b)
}
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbl1q_s8 (int8x16_t a, int8x16_t b)
+vqtbl1q_s8 (int8x16_t a, uint8x16_t b)
{
int8x16_t result;
__asm__ ("tbl %0.16b, {%1.16b}, %2.16b"
@@ -16028,7 +16028,7 @@ vqtbl1q_u8 (uint8x16_t a, uint8x16_t b)
}
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbl2_s8 (int8x16x2_t tab, int8x8_t idx)
+vqtbl2_s8 (int8x16x2_t tab, uint8x8_t idx)
{
int8x8_t result;
__asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
@@ -16064,7 +16064,7 @@ vqtbl2_p8 (poly8x16x2_t tab, uint8x8_t idx)
}
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbl2q_s8 (int8x16x2_t tab, int8x16_t idx)
+vqtbl2q_s8 (int8x16x2_t tab, uint8x16_t idx)
{
int8x16_t result;
__asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
@@ -16100,7 +16100,7 @@ vqtbl2q_p8 (poly8x16x2_t tab, uint8x16_t idx)
}
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbl3_s8 (int8x16x3_t tab, int8x8_t idx)
+vqtbl3_s8 (int8x16x3_t tab, uint8x8_t idx)
{
int8x8_t result;
__asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
@@ -16136,7 +16136,7 @@ vqtbl3_p8 (poly8x16x3_t tab, uint8x8_t idx)
}
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbl3q_s8 (int8x16x3_t tab, int8x16_t idx)
+vqtbl3q_s8 (int8x16x3_t tab, uint8x16_t idx)
{
int8x16_t result;
__asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
@@ -16172,7 +16172,7 @@ vqtbl3q_p8 (poly8x16x3_t tab, uint8x16_t idx)
}
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbl4_s8 (int8x16x4_t tab, int8x8_t idx)
+vqtbl4_s8 (int8x16x4_t tab, uint8x8_t idx)
{
int8x8_t result;
__asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
@@ -16209,7 +16209,7 @@ vqtbl4_p8 (poly8x16x4_t tab, uint8x8_t idx)
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbl4q_s8 (int8x16x4_t tab, int8x16_t idx)
+vqtbl4q_s8 (int8x16x4_t tab, uint8x16_t idx)
{
int8x16_t result;
__asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
@@ -16246,7 +16246,7 @@ vqtbl4q_p8 (poly8x16x4_t tab, uint8x16_t idx)
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbx1_s8 (int8x8_t r, int8x16_t tab, int8x8_t idx)
+vqtbx1_s8 (int8x8_t r, int8x16_t tab, uint8x8_t idx)
{
int8x8_t result = r;
__asm__ ("tbx %0.8b,{%1.16b},%2.8b"
@@ -16279,7 +16279,7 @@ vqtbx1_p8 (poly8x8_t r, poly8x16_t tab, uint8x8_t idx)
}
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbx1q_s8 (int8x16_t r, int8x16_t tab, int8x16_t idx)
+vqtbx1q_s8 (int8x16_t r, int8x16_t tab, uint8x16_t idx)
{
int8x16_t result = r;
__asm__ ("tbx %0.16b,{%1.16b},%2.16b"
@@ -16312,7 +16312,7 @@ vqtbx1q_p8 (poly8x16_t r, poly8x16_t tab, uint8x16_t idx)
}
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbx2_s8 (int8x8_t r, int8x16x2_t tab, int8x8_t idx)
+vqtbx2_s8 (int8x8_t r, int8x16x2_t tab, uint8x8_t idx)
{
int8x8_t result = r;
__asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
@@ -16349,7 +16349,7 @@ vqtbx2_p8 (poly8x8_t r, poly8x16x2_t tab, uint8x8_t idx)
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbx2q_s8 (int8x16_t r, int8x16x2_t tab, int8x16_t idx)
+vqtbx2q_s8 (int8x16_t r, int8x16x2_t tab, uint8x16_t idx)
{
int8x16_t result = r;
__asm__ ("ld1 {v16.16b, v17.16b}, %1\n\t"
@@ -16386,7 +16386,7 @@ vqtbx2q_p8 (poly8x16_t r, poly8x16x2_t tab, uint8x16_t idx)
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbx3_s8 (int8x8_t r, int8x16x3_t tab, int8x8_t idx)
+vqtbx3_s8 (int8x8_t r, int8x16x3_t tab, uint8x8_t idx)
{
int8x8_t result = r;
__asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
@@ -16423,7 +16423,7 @@ vqtbx3_p8 (poly8x8_t r, poly8x16x3_t tab, uint8x8_t idx)
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbx3q_s8 (int8x16_t r, int8x16x3_t tab, int8x16_t idx)
+vqtbx3q_s8 (int8x16_t r, int8x16x3_t tab, uint8x16_t idx)
{
int8x16_t result = r;
__asm__ ("ld1 {v16.16b - v18.16b}, %1\n\t"
@@ -16460,7 +16460,7 @@ vqtbx3q_p8 (poly8x16_t r, poly8x16x3_t tab, uint8x16_t idx)
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vqtbx4_s8 (int8x8_t r, int8x16x4_t tab, int8x8_t idx)
+vqtbx4_s8 (int8x8_t r, int8x16x4_t tab, uint8x8_t idx)
{
int8x8_t result = r;
__asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
@@ -16497,7 +16497,7 @@ vqtbx4_p8 (poly8x8_t r, poly8x16x4_t tab, uint8x8_t idx)
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vqtbx4q_s8 (int8x16_t r, int8x16x4_t tab, int8x16_t idx)
+vqtbx4q_s8 (int8x16_t r, int8x16x4_t tab, uint8x16_t idx)
{
int8x16_t result = r;
__asm__ ("ld1 {v16.16b - v19.16b}, %1\n\t"
diff --git a/gcc/testsuite/gcc.target/aarch64/table-intrinsics.c b/gcc/testsuite/gcc.target/aarch64/table-intrinsics.c
index 5d53abe..6281cda 100644
--- a/gcc/testsuite/gcc.target/aarch64/table-intrinsics.c
+++ b/gcc/testsuite/gcc.target/aarch64/table-intrinsics.c
@@ -148,7 +148,7 @@ tb_testp8_4 (poly8x8_t r, poly8x8x4_t tab, uint8x8_t idx)
}
int8x8_t
-qtbl_tests8_ (int8x16_t tab, int8x8_t idx)
+qtbl_tests8_ (int8x16_t tab, uint8x8_t idx)
{
return vqtbl1_s8 (tab, idx);
}
@@ -166,7 +166,7 @@ qtbl_testp8_ (poly8x16_t tab, uint8x8_t idx)
}
int8x8_t
-qtbl_tests8_2 (int8x16x2_t tab, int8x8_t idx)
+qtbl_tests8_2 (int8x16x2_t tab, uint8x8_t idx)
{
return vqtbl2_s8 (tab, idx);
}
@@ -184,7 +184,7 @@ qtbl_testp8_2 (poly8x16x2_t tab, uint8x8_t idx)
}
int8x8_t
-qtbl_tests8_3 (int8x16x3_t tab, int8x8_t idx)
+qtbl_tests8_3 (int8x16x3_t tab, uint8x8_t idx)
{
return vqtbl3_s8 (tab, idx);
}
@@ -202,7 +202,7 @@ qtbl_testp8_3 (poly8x16x3_t tab, uint8x8_t idx)
}
int8x8_t
-qtbl_tests8_4 (int8x16x4_t tab, int8x8_t idx)
+qtbl_tests8_4 (int8x16x4_t tab, uint8x8_t idx)
{
return vqtbl4_s8 (tab, idx);
}
@@ -220,7 +220,7 @@ qtbl_testp8_4 (poly8x16x4_t tab, uint8x8_t idx)
}
int8x8_t
-qtb_tests8_ (int8x8_t r, int8x16_t tab, int8x8_t idx)
+qtb_tests8_ (int8x8_t r, int8x16_t tab, uint8x8_t idx)
{
return vqtbx1_s8 (r, tab, idx);
}
@@ -238,7 +238,7 @@ qtb_testp8_ (poly8x8_t r, poly8x16_t tab, uint8x8_t idx)
}
int8x8_t
-qtb_tests8_2 (int8x8_t r, int8x16x2_t tab, int8x8_t idx)
+qtb_tests8_2 (int8x8_t r, int8x16x2_t tab, uint8x8_t idx)
{
return vqtbx2_s8 (r, tab, idx);
}
@@ -256,7 +256,7 @@ qtb_testp8_2 (poly8x8_t r, poly8x16x2_t tab, uint8x8_t idx)
}
int8x8_t
-qtb_tests8_3 (int8x8_t r, int8x16x3_t tab, int8x8_t idx)
+qtb_tests8_3 (int8x8_t r, int8x16x3_t tab, uint8x8_t idx)
{
return vqtbx3_s8 (r, tab, idx);
}
@@ -274,7 +274,7 @@ qtb_testp8_3 (poly8x8_t r, poly8x16x3_t tab, uint8x8_t idx)
}
int8x8_t
-qtb_tests8_4 (int8x8_t r, int8x16x4_t tab, int8x8_t idx)
+qtb_tests8_4 (int8x8_t r, int8x16x4_t tab, uint8x8_t idx)
{
return vqtbx4_s8 (r, tab, idx);
}
@@ -292,7 +292,7 @@ qtb_testp8_4 (poly8x8_t r, poly8x16x4_t tab, uint8x8_t idx)
}
int8x16_t
-qtblq_tests8_ (int8x16_t tab, int8x16_t idx)
+qtblq_tests8_ (int8x16_t tab, uint8x16_t idx)
{
return vqtbl1q_s8 (tab, idx);
}
@@ -310,7 +310,7 @@ qtblq_testp8_ (poly8x16_t tab, uint8x16_t idx)
}
int8x16_t
-qtblq_tests8_2 (int8x16x2_t tab, int8x16_t idx)
+qtblq_tests8_2 (int8x16x2_t tab, uint8x16_t idx)
{
return vqtbl2q_s8 (tab, idx);
}
@@ -328,7 +328,7 @@ qtblq_testp8_2 (poly8x16x2_t tab, uint8x16_t idx)
}
int8x16_t
-qtblq_tests8_3 (int8x16x3_t tab, int8x16_t idx)
+qtblq_tests8_3 (int8x16x3_t tab, uint8x16_t idx)
{
return vqtbl3q_s8 (tab, idx);
}
@@ -346,7 +346,7 @@ qtblq_testp8_3 (poly8x16x3_t tab, uint8x16_t idx)
}
int8x16_t
-qtblq_tests8_4 (int8x16x4_t tab, int8x16_t idx)
+qtblq_tests8_4 (int8x16x4_t tab, uint8x16_t idx)
{
return vqtbl4q_s8 (tab, idx);
}
@@ -364,7 +364,7 @@ qtblq_testp8_4 (poly8x16x4_t tab, uint8x16_t idx)
}
int8x16_t
-qtbxq_tests8_ (int8x16_t r, int8x16_t tab, int8x16_t idx)
+qtbxq_tests8_ (int8x16_t r, int8x16_t tab, uint8x16_t idx)
{
return vqtbx1q_s8 (r, tab, idx);
}
@@ -382,7 +382,7 @@ qtbxq_testp8_ (poly8x16_t r, poly8x16_t tab, uint8x16_t idx)
}
int8x16_t
-qtbxq_tests8_2 (int8x16_t r, int8x16x2_t tab, int8x16_t idx)
+qtbxq_tests8_2 (int8x16_t r, int8x16x2_t tab, uint8x16_t idx)
{
return vqtbx2q_s8 (r, tab, idx);
}
@@ -400,7 +400,7 @@ qtbxq_testp8_2 (poly8x16_t r, poly8x16x2_t tab, uint8x16_t idx)
}
int8x16_t
-qtbxq_tests8_3 (int8x16_t r, int8x16x3_t tab, int8x16_t idx)
+qtbxq_tests8_3 (int8x16_t r, int8x16x3_t tab, uint8x16_t idx)
{
return vqtbx3q_s8 (r, tab, idx);
}
@@ -418,7 +418,7 @@ qtbxq_testp8_3 (poly8x16_t r, poly8x16x3_t tab, uint8x16_t idx)
}
int8x16_t
-qtbxq_tests8_4 (int8x16_t r, int8x16x4_t tab, int8x16_t idx)
+qtbxq_tests8_4 (int8x16_t r, int8x16x4_t tab, uint8x16_t idx)
{
return vqtbx4q_s8 (r, tab, idx);
}
