On 29 October 2013 03:24, Ramana Radhakrishnan <[email protected]> wrote:
> On 10/09/13 23:16, Christophe Lyon wrote:
> Irrespective of our earlier conversations on this now I'm actually wondering
> if instead of doing this and integrating this in the GCC source base it
> maybe easier to write a harness to test this cross on qemu or natively.
> Additionally setting up an auto-tester to do this might be a more productive
> use of time rather than manually dejagnuizing this which appears to be a
> tedious and slow process.
This would be easy to setup, since the Makefile on gitorious is
already targetting qemu. I used it occasionnally on boards with
minimal changes.
This just means we'd have to agree on how to set up such an
auto-tester, where do we send the results to, etc...
>> I'd like your feedback before continuing, as there are a lot more
>> files to come.
>>
>> I have made some cleanup to help review, but the two .h files will
>> need to grow as more intrinsics will be added (see the original ones).
>
> Which one should I compare this with in terms of the original file ?
I have kept the same file names.
>> I'd like to keep the modifications at a minimal level, to save my time
>> when adapting each test (there are currently 145 test files, so 143
>> left:-).
>
>
> On to the patch itself.
>
> The prefix TEST_ seems a bit misleading in that it suggests this is testing
> something when in reality this is initializing stuff.
In fact, TEST_XXXX executes the XXXX intrinsics, and copies the
results to memory when relevant. But I can easily change TEST_ to
something else.
So in the sample I posted:
TEST_VABA: VAR=vaba(....); vst1(BUFFER,VAR)
TEST_VLD1: VAR=vld1(....); vst1(BUFFER, VAR)
VDUP is special in that it is a helper for other tests:
TEST_VDUP: VAR1=vdup(VAR2,xxxx)
and similarly for TEST_VLOAD and TEST_VSETLANE
>> +# Exit immediately if this isn't an ARM target.
>> +if ![istarget arm*-*-*] then {
>> + return
>> +}
>
>
> Also for aarch64*-*-* as all these intrinsics are compatible with the
> aarch64 port. I would also prefer that this be tortured over multiple
> optimization levels as many times we find issues with different optimization
> levels.
OK, this sounds easy to do, and I agree. I prefered to post a simple
version first.
And given you talked me about your plans to factorize arm and aarch64
tests, I thought it was better to start with a simple version I knew
was working.
> More later I need to get back to something else and I need to play more with
> your original testsuite - but I'd like some discussion around some of these
> points anyway.
>
> Ramana
OK thanks for the feedback. If we decide to go with auto-testers
instead, the discussion will probably be shorter.
Christophe
>
>> +
>> +# Load support procs.
>> +load_lib gcc-dg.exp
>> +
>> +# Initialize `dg'.
>> +dg-init
>> +
>> +# Main loop.
>> +gcc-dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*.\[cCS\]]] \
>> + ""
>> +
>> +# All done.
>> +dg-finish
>> diff -rNup '--exclude=.git'
>> gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/arm-neon-ref.h
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/arm-neon-ref.h
>> --- gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/arm-neon-ref.h
>> 1970-01-01 01:00:00.000000000 +0100
>> +++
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/arm-neon-ref.h
>> 2013-05-09 00:48:59.395628726 +0200
>> @@ -0,0 +1,349 @@
>> +#ifndef_ARM_NEON_REF_H_
>> +#define_ARM_NEON_REF_H_
>> +
>> +#include <stdio.h>
>> +#include <inttypes.h>
>> +#include <string.h>
>> +#include <stdlib.h>
>> +
>> +#define xSTR(X) #X
>> +#define STR(X) xSTR(X)
>> +
>> +#define xNAME1(V,T) V ## _ ## T
>> +#define xNAME(V,T) xNAME1(V,T)
>> +
>> +#define VAR(V,T,W) xNAME(V,T##W)
>> +#define VAR_DECL(V, T, W) T##W##_t VAR(V,T,W)
>> +
>> +#define VECT_NAME(T, W, N) T##W##x##N
>> +#define VECT_ARRAY_NAME(T, W, N, L) T##W##x##N##x##L
>> +#define VECT_TYPE(T, W, N) xNAME(VECT_NAME(T,W,N),t)
>> +#define VECT_ARRAY_TYPE(T, W, N, L) xNAME(VECT_ARRAY_NAME(T,W,N,L),t)
>> +
>> +#define VECT_VAR(V,T,W,N) xNAME(V,VECT_NAME(T,W,N))
>> +#define VECT_VAR_DECL(V, T, W, N) T##W##_t VECT_VAR(V,T,W,N)
>> +
>> +/* Array declarations. */
>> +#define ARRAY(V, T, W, N) VECT_VAR_DECL(V,T,W,N)[N]
>> +
>> +/* Check results vs expected values. */
>> +#define CHECK(MSG,T,W,N,FMT) \
>> + for(i=0; i<N ; i++) \
>> + { \
>> + if (VECT_VAR(result, T, W, N)[i] != VECT_VAR(expected, T, W, N)[i])
>> { \
>> + fprintf(stderr, \
>> + "ERROR in %s at type %s index %d: 0x%" FMT " != 0x%" \
>> + FMT " (expected)\n", \
>> + MSG, STR(VECT_NAME(T, W, N)), i, \
>> + VECT_VAR(result, T, W, N)[i], \
>> + VECT_VAR(expected, T, W, N)[i]); \
>> + abort(); \
>> + }
>> \
>> + }
>> +
>> +/* Floating-point variant. */
>> +#define CHECK_FP(MSG,T,W,N,FMT)
>> \
>> + for(i=0; i<N ; i++) \
>> + { \
>> + union fp_operand { \
>> + uint##W##_t i; \
>> + float##W##_t f; \
>> + } tmp_res, tmp_exp; \
>> + tmp_res.f = VECT_VAR(result, T, W, N)[i];
>> \
>> + tmp_exp.f = VECT_VAR(expected, T, W, N)[i]; \
>> + if (tmp_res.i != tmp_exp.i) { \
>> + fprintf(stderr, \
>> + "ERROR in %s at type %s index %d: 0x%" FMT " != 0x%" \
>> + FMT " (expected)\n", \
>> + MSG, STR(VECT_NAME(T, W, N)), i, \
>> + tmp_res.i, \
>> + tmp_exp.i); \
>> + abort(); \
>> + }
>> \
>> + }
>> +
>> +/* Clean buffer with a non-zero pattern. */
>> +#define CLEAN_PATTERN_8 0x33
>> +
>> +#define CLEAN(VAR,T,W,N) \
>> + memset(VECT_VAR(VAR, T, W, N), \
>> + CLEAN_PATTERN_8, \
>> + sizeof(VECT_VAR(VAR, T, W, N)));
>> +
>> +/* Input buffers, one of each size. */
>> +extern ARRAY(buffer, int, 8, 8);
>> +extern ARRAY(buffer, int, 16, 4);
>> +extern ARRAY(buffer, int, 32, 2);
>> +extern ARRAY(buffer, int, 64, 1);
>> +extern ARRAY(buffer, uint, 8, 8);
>> +extern ARRAY(buffer, uint, 16, 4);
>> +extern ARRAY(buffer, uint, 32, 2);
>> +extern ARRAY(buffer, uint, 64, 1);
>> +extern ARRAY(buffer, poly, 8, 8);
>> +extern ARRAY(buffer, poly, 16, 4);
>> +extern ARRAY(buffer, float, 32, 2);
>> +extern ARRAY(buffer, int, 8, 16);
>> +extern ARRAY(buffer, int, 16, 8);
>> +extern ARRAY(buffer, int, 32, 4);
>> +extern ARRAY(buffer, int, 64, 2);
>> +extern ARRAY(buffer, uint, 8, 16);
>> +extern ARRAY(buffer, uint, 16, 8);
>> +extern ARRAY(buffer, uint, 32, 4);
>> +extern ARRAY(buffer, uint, 64, 2);
>> +extern ARRAY(buffer, poly, 8, 16);
>> +extern ARRAY(buffer, poly, 16, 8);
>> +extern ARRAY(buffer, float, 32, 4);
>> +
>> +/* Output buffers, one of each size. */
>> +static ARRAY(result, int, 8, 8);
>> +static ARRAY(result, int, 16, 4);
>> +static ARRAY(result, int, 32, 2);
>> +static ARRAY(result, int, 64, 1);
>> +static ARRAY(result, uint, 8, 8);
>> +static ARRAY(result, uint, 16, 4);
>> +static ARRAY(result, uint, 32, 2);
>> +static ARRAY(result, uint, 64, 1);
>> +static ARRAY(result, poly, 8, 8);
>> +static ARRAY(result, poly, 16, 4);
>> +static ARRAY(result, float, 32, 2);
>> +static ARRAY(result, int, 8, 16);
>> +static ARRAY(result, int, 16, 8);
>> +static ARRAY(result, int, 32, 4);
>> +static ARRAY(result, int, 64, 2);
>> +static ARRAY(result, uint, 8, 16);
>> +static ARRAY(result, uint, 16, 8);
>> +static ARRAY(result, uint, 32, 4);
>> +static ARRAY(result, uint, 64, 2);
>> +static ARRAY(result, poly, 8, 16);
>> +static ARRAY(result, poly, 16, 8);
>> +static ARRAY(result, float, 32, 4);
>> +
>> +/* Expected results, one of each size. */
>> +extern ARRAY(expected, int, 8, 8);
>> +extern ARRAY(expected, int, 16, 4);
>> +extern ARRAY(expected, int, 32, 2);
>> +extern ARRAY(expected, int, 64, 1);
>> +extern ARRAY(expected, uint, 8, 8);
>> +extern ARRAY(expected, uint, 16, 4);
>> +extern ARRAY(expected, uint, 32, 2);
>> +extern ARRAY(expected, uint, 64, 1);
>> +extern ARRAY(expected, poly, 8, 8);
>> +extern ARRAY(expected, poly, 16, 4);
>> +extern ARRAY(expected, float, 32, 2);
>> +extern ARRAY(expected, int, 8, 16);
>> +extern ARRAY(expected, int, 16, 8);
>> +extern ARRAY(expected, int, 32, 4);
>> +extern ARRAY(expected, int, 64, 2);
>> +extern ARRAY(expected, uint, 8, 16);
>> +extern ARRAY(expected, uint, 16, 8);
>> +extern ARRAY(expected, uint, 32, 4);
>> +extern ARRAY(expected, uint, 64, 2);
>> +extern ARRAY(expected, poly, 8, 16);
>> +extern ARRAY(expected, poly, 16, 8);
>> +extern ARRAY(expected, float, 32, 4);
>> +
>> +/* Check results. */
>> +static void check_results (const char*test_name, const char* comment)
>> +{
>> + int i;
>> +
>> + CHECK(test_name, int, 8, 8, PRIx8);
>> + CHECK(test_name, int, 16, 4, PRIx16);
>> + CHECK(test_name, int, 32, 2, PRIx32);
>> + CHECK(test_name, int, 64, 1, PRIx64);
>> + CHECK(test_name, uint, 8, 8, PRIx8);
>> + CHECK(test_name, uint, 16, 4, PRIx16);
>> + CHECK(test_name, uint, 32, 2, PRIx32);
>> + CHECK(test_name, uint, 64, 1, PRIx64);
>> + CHECK(test_name, poly, 8, 8, PRIx8);
>> + CHECK(test_name, poly, 16, 4, PRIx16);
>> + CHECK_FP(test_name, float, 32, 2, PRIx32);
>> +
>> + CHECK(test_name, int, 8, 16, PRIx8);
>> + CHECK(test_name, int, 16, 8, PRIx16);
>> + CHECK(test_name, int, 32, 4, PRIx32);
>> + CHECK(test_name, int, 64, 2, PRIx64);
>> + CHECK(test_name, uint, 8, 16, PRIx8);
>> + CHECK(test_name, uint, 16, 8, PRIx16);
>> + CHECK(test_name, uint, 32, 4, PRIx32);
>> + CHECK(test_name, uint, 64, 2, PRIx64);
>> + CHECK(test_name, poly, 8, 16, PRIx8);
>> + CHECK(test_name, poly, 16, 8, PRIx16);
>> + CHECK_FP(test_name, float, 32, 4, PRIx32);
>> +}
>> +
>> +/* Clean output buffers before execution. */
>> +static void clean_results (void)
>> +{
>> + CLEAN(result, int, 8, 8);
>> + CLEAN(result, int, 16, 4);
>> + CLEAN(result, int, 32, 2);
>> + CLEAN(result, int, 64, 1);
>> + CLEAN(result, uint, 8, 8);
>> + CLEAN(result, uint, 16, 4);
>> + CLEAN(result, uint, 32, 2);
>> + CLEAN(result, uint, 64, 1);
>> + CLEAN(result, poly, 8, 8);
>> + CLEAN(result, poly, 16, 4);
>> + CLEAN(result, float, 32, 2);
>> +
>> + CLEAN(result, int, 8, 16);
>> + CLEAN(result, int, 16, 8);
>> + CLEAN(result, int, 32, 4);
>> + CLEAN(result, int, 64, 2);
>> + CLEAN(result, uint, 8, 16);
>> + CLEAN(result, uint, 16, 8);
>> + CLEAN(result, uint, 32, 4);
>> + CLEAN(result, uint, 64, 2);
>> + CLEAN(result, poly, 8, 16);
>> + CLEAN(result, poly, 16, 8);
>> + CLEAN(result, float, 32, 4);
>> +}
>> +
>> +
>> +/* Helpers to declare variables of various types. */
>> +#define DECL_VARIABLE(VAR, T1, W, N) \
>> + VECT_TYPE(T1, W, N) VECT_VAR(VAR, T1, W, N)
>> +
>> +#define DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR) \
>> + DECL_VARIABLE(VAR, int, 8, 8); \
>> + DECL_VARIABLE(VAR, int, 16, 4); \
>> + DECL_VARIABLE(VAR, int, 32, 2); \
>> + DECL_VARIABLE(VAR, int, 64, 1)
>> +
>> +#define DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR) \
>> + DECL_VARIABLE(VAR, uint, 8, 8); \
>> + DECL_VARIABLE(VAR, uint, 16, 4); \
>> + DECL_VARIABLE(VAR, uint, 32, 2); \
>> + DECL_VARIABLE(VAR, uint, 64, 1)
>> +
>> +#define DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR) \
>> + DECL_VARIABLE(VAR, int, 8, 16); \
>> + DECL_VARIABLE(VAR, int, 16, 8); \
>> + DECL_VARIABLE(VAR, int, 32, 4); \
>> + DECL_VARIABLE(VAR, int, 64, 2)
>> +
>> +#define DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR) \
>> + DECL_VARIABLE(VAR, uint, 8, 16); \
>> + DECL_VARIABLE(VAR, uint, 16, 8); \
>> + DECL_VARIABLE(VAR, uint, 32, 4); \
>> + DECL_VARIABLE(VAR, uint, 64, 2)
>> +
>> +#define DECL_VARIABLE_64BITS_VARIANTS(VAR) \
>> + DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR); \
>> + DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR); \
>> + DECL_VARIABLE(VAR, poly, 8, 8); \
>> + DECL_VARIABLE(VAR, poly, 16, 4); \
>> + DECL_VARIABLE(VAR, float, 32, 2)
>> +
>> +#define DECL_VARIABLE_128BITS_VARIANTS(VAR) \
>> + DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR); \
>> + DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR); \
>> + DECL_VARIABLE(VAR, poly, 8, 16); \
>> + DECL_VARIABLE(VAR, poly, 16, 8); \
>> + DECL_VARIABLE(VAR, float, 32, 4)
>> +
>> +#define DECL_VARIABLE_ALL_VARIANTS(VAR) \
>> + DECL_VARIABLE_64BITS_VARIANTS(VAR); \
>> + DECL_VARIABLE_128BITS_VARIANTS(VAR)
>> +
>> +/* Helpers to initialize vectors. */
>> +#define TEST_VDUP(VAR, Q, T1, T2, W, N, V) \
>> + VECT_VAR(VAR, T1, W, N) = vdup##Q##_n_##T2##W(V)
>> +
>> +#define TEST_VSET_LANE(VAR, Q, T1, T2, W, N, L, V) \
>> + VECT_VAR(VAR, T1, W, N) = vset##Q##_lane_##T2##W(V, \
>> + VECT_VAR(VAR, T1, W,
>> N), \
>> + L)
>> +
>> +/* We need to load initial values first, so rely on VLD1. */
>> +#define TEST_VLOAD(VAR, BUF, Q, T1, T2, W, N) \
>> + VECT_VAR(VAR, T1, W, N) = vld1##Q##_##T2##W(VECT_VAR(BUF, T1, W, N))
>> +
>> +/* Helpers for macros with 1 constant and 5 variable arguments. */
>> +#define TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR) \
>> + MACRO(VAR, , int, s, 8, 8); \
>> + MACRO(VAR, , int, s, 16, 4); \
>> + MACRO(VAR, , int, s, 32, 2); \
>> + MACRO(VAR, , int, s, 64, 1)
>> +
>> +#define TEST_MACRO_64BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR) \
>> + MACRO(VAR, , uint, u, 8, 8); \
>> + MACRO(VAR, , uint, u, 16, 4); \
>> + MACRO(VAR, , uint, u, 32, 2); \
>> + MACRO(VAR, , uint, u, 64, 1)
>> +
>> +#define TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR) \
>> + MACRO(VAR, q, int, s, 8, 16); \
>> + MACRO(VAR, q, int, s, 16, 8); \
>> + MACRO(VAR, q, int, s, 32, 4); \
>> + MACRO(VAR, q, int, s, 64, 2)
>> +
>> +#define TEST_MACRO_128BITS_UNSIGNED_VARIANTS_1_5(MACRO,VAR) \
>> + MACRO(VAR, q, uint, u, 8, 16); \
>> + MACRO(VAR, q, uint, u, 16, 8); \
>> + MACRO(VAR, q, uint, u, 32, 4); \
>> + MACRO(VAR, q, uint, u, 64, 2)
>> +
>> +#define TEST_MACRO_64BITS_VARIANTS_1_5(MACRO, VAR) \
>> + TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR); \
>> + TEST_MACRO_64BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR)
>> +
>> +#define TEST_MACRO_128BITS_VARIANTS_1_5(MACRO, VAR) \
>> + TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR); \
>> + TEST_MACRO_128BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR)
>> +
>> +#define TEST_MACRO_ALL_VARIANTS_1_5(MACRO, VAR) \
>> + TEST_MACRO_64BITS_VARIANTS_1_5(MACRO, VAR); \
>> + TEST_MACRO_128BITS_VARIANTS_1_5(MACRO, VAR)
>> +
>> +#define TEST_MACRO_SIGNED_VARIANTS_1_5(MACRO, VAR) \
>> + TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR); \
>> + TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR)
>> +
>> +/* Helpers for macros with 2 constant and 5 variable arguments. */
>> +#define TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + MACRO(VAR1, VAR2, , int, s, 8, 8); \
>> + MACRO(VAR1, VAR2, , int, s, 16, 4); \
>> + MACRO(VAR1, VAR2, , int, s, 32, 2); \
>> + MACRO(VAR1, VAR2 , , int, s, 64, 1)
>> +
>> +#define TEST_MACRO_64BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + MACRO(VAR1, VAR2, , uint, u, 8, 8); \
>> + MACRO(VAR1, VAR2, , uint, u, 16, 4); \
>> + MACRO(VAR1, VAR2, , uint, u, 32, 2); \
>> + MACRO(VAR1, VAR2, , uint, u, 64, 1)
>> +
>> +#define TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + MACRO(VAR1, VAR2, q, int, s, 8, 16); \
>> + MACRO(VAR1, VAR2, q, int, s, 16, 8); \
>> + MACRO(VAR1, VAR2, q, int, s, 32, 4); \
>> + MACRO(VAR1, VAR2, q, int, s, 64, 2)
>> +
>> +#define TEST_MACRO_128BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + MACRO(VAR1, VAR2, q, uint, u, 8, 16);
>> \
>> + MACRO(VAR1, VAR2, q, uint, u, 16, 8);
>> \
>> + MACRO(VAR1, VAR2, q, uint, u, 32, 4);
>> \
>> + MACRO(VAR1, VAR2, q, uint, u, 64, 2)
>> +
>> +#define TEST_MACRO_64BITS_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
>> + TEST_MACRO_64BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
>> + MACRO(VAR1, VAR2, , poly, p, 8, 8); \
>> + MACRO(VAR1, VAR2, , poly, p, 16, 4)
>> +
>> +#define TEST_MACRO_128BITS_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
>> + TEST_MACRO_128BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
>> + MACRO(VAR1, VAR2, q, poly, p, 8, 16); \
>> + MACRO(VAR1, VAR2, q, poly, p, 16, 8)
>> +
>> +#define TEST_MACRO_ALL_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + TEST_MACRO_64BITS_VARIANTS_2_5(MACRO, VAR1, VAR2); \
>> + TEST_MACRO_128BITS_VARIANTS_2_5(MACRO, VAR1, VAR2)
>> +
>> +#define TEST_MACRO_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
>> + TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
>> + TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)
>> +
>> +#endif /*_ARM_NEON_REF_H_ */
>> diff -rNup '--exclude=.git'
>> gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/compute_ref_data.h
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/compute_ref_data.h
>> ---
>> gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/compute_ref_data.h
>> 1970-01-01 01:00:00.000000000 +0100
>> +++
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/compute_ref_data.h
>> 2013-05-09 00:31:03.563656926 +0200
>> @@ -0,0 +1,80 @@
>> +#include <arm_neon.h>
>> +#include "arm-neon-ref.h"
>> +
>> +/* Initialization helpers; 4 slices are needed for vld2, vld3 and
>> + vld4. */
>> +#define MY_INIT_TAB(T,W,N) xNAME(INIT_TAB,N)(T##W##_t)
>> +#define MY_INIT_TAB2(T,W,N) xNAME(INIT_TAB2,N)(T##W##_t)
>> +#define MY_INIT_TAB3(T,W,N) xNAME(INIT_TAB3,N)(T##W##_t)
>> +#define MY_INIT_TAB4(T,W,N) xNAME(INIT_TAB4,N)(T##W##_t)
>> +
>> +/* Initialized input buffers. */
>> +#define VECT_VAR_DECL_INIT(V, T, W, N) \
>> + VECT_VAR_DECL(V,T,W,N) [] = { MY_INIT_TAB(T,W,N) };
>> +
>> +/* Sample initialization vectors. */
>> +#define INIT_TAB_1(T) \
>> + (T)-16,
>> +
>> +#define INIT_TAB_2(T) \
>> + (T)-16, (T)-15,
>> +
>> +#define INIT_TAB_4(T) \
>> + (T)-16, (T)-15, (T)-14, (T)-13,
>> +
>> +#define INIT_TAB_8(T) \
>> + (T)-16, (T)-15, (T)-14, (T)-13, (T)-12, (T)-11, (T)-10, (T)-9,
>> +
>> +#define INIT_TAB_16(T) \
>> + (T)-16, (T)-15, (T)-14, (T)-13, (T)-12, (T)-11, (T)-10, (T)-9, \
>> + (T)-8, (T)-7, (T)-6, (T)-5, (T)-4, (T)-3, (T)-2, (T)-1,
>> +
>> +/* This one is used for padding between input buffers. */
>> +#define PAD(V, T, W, N) char VECT_VAR(V,T,W,N)=42;
>> +
>> +/* Input buffers, one of each size. */
>> +/* Insert some padding to try to exhibit out of bounds accesses. */
>> +VECT_VAR_DECL_INIT(buffer, int, 8, 8);
>> +PAD(buffer_pad, int, 8, 8);
>> +VECT_VAR_DECL_INIT(buffer, int, 16, 4);
>> +PAD(buffer_pad, int, 16, 4);
>> +VECT_VAR_DECL_INIT(buffer, int, 32, 2);
>> +PAD(buffer_pad, int, 32, 2);
>> +VECT_VAR_DECL_INIT(buffer, int, 64, 1);
>> +PAD(buffer_pad, int, 64, 1);
>> +VECT_VAR_DECL_INIT(buffer, uint, 8, 8);
>> +PAD(buffer_pad, uint, 8, 8);
>> +VECT_VAR_DECL_INIT(buffer, poly, 8, 8);
>> +PAD(buffer_pad, poly, 8, 8);
>> +VECT_VAR_DECL_INIT(buffer, poly, 16, 4);
>> +PAD(buffer_pad, poly, 16, 4);
>> +VECT_VAR_DECL_INIT(buffer, uint, 16, 4);
>> +PAD(buffer_pad, uint, 16, 4);
>> +VECT_VAR_DECL_INIT(buffer, uint, 32, 2);
>> +PAD(buffer_pad, uint, 32, 2);
>> +VECT_VAR_DECL_INIT(buffer, uint, 64, 1);
>> +PAD(buffer_pad, uint, 64, 1);
>> +VECT_VAR_DECL_INIT(buffer, float, 32, 2);
>> +PAD(buffer_pad, float, 32, 2);
>> +VECT_VAR_DECL_INIT(buffer, int, 8, 16);
>> +PAD(buffer_pad, int, 8, 16);
>> +VECT_VAR_DECL_INIT(buffer, int, 16, 8);
>> +PAD(buffer_pad, int, 16, 8);
>> +VECT_VAR_DECL_INIT(buffer, int, 32, 4);
>> +PAD(buffer_pad, int, 32, 4);
>> +VECT_VAR_DECL_INIT(buffer, int, 64, 2);
>> +PAD(buffer_pad, int, 64, 2);
>> +VECT_VAR_DECL_INIT(buffer, uint, 8, 16);
>> +PAD(buffer_pad, uint, 8, 16);
>> +VECT_VAR_DECL_INIT(buffer, uint, 16, 8);
>> +PAD(buffer_pad, uint, 16, 8);
>> +VECT_VAR_DECL_INIT(buffer, uint, 32, 4);
>> +PAD(buffer_pad, uint, 32, 4);
>> +VECT_VAR_DECL_INIT(buffer, uint, 64, 2);
>> +PAD(buffer_pad, uint, 64, 2);
>> +VECT_VAR_DECL_INIT(buffer, poly, 8, 16);
>> +PAD(buffer_pad, poly, 8, 16);
>> +VECT_VAR_DECL_INIT(buffer, poly, 16, 8);
>> +PAD(buffer_pad, poly, 16, 8);
>> +VECT_VAR_DECL_INIT(buffer, float, 32, 4);
>> +PAD(buffer_pad, float, 32, 4);
>> diff -rNup '--exclude=.git'
>> gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vaba.c
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vaba.c
>> --- gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vaba.c
>> 1970-01-01 01:00:00.000000000 +0100
>> +++
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vaba.c
>> 2013-05-09 00:40:27.611642141 +0200
>> @@ -0,0 +1,145 @@
>> +/* { dg-do run } */
>> +/* { dg-require-effective-target arm_neon_hw } */
>> +/* { dg-add-options arm_neon } */
>> +
>> +#include <arm_neon.h>
>> +#include "arm-neon-ref.h"
>> +#include "compute_ref_data.h"
>> +
>> +VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf7, 0xf8, 0xf9,
>> + 0xfa, 0xfb, 0xfc, 0xfd };
>> +VECT_VAR_DECL(expected,int,16,4) [] = { 0x16, 0x17, 0x18, 0x19 };
>> +VECT_VAR_DECL(expected,int,32,2) [] = { 0x20, 0x21 };
>> +VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
>> +VECT_VAR_DECL(expected,uint,8,8) [] = { 0x53, 0x54, 0x55, 0x56,
>> + 0x57, 0x58, 0x59, 0x5a };
>> +VECT_VAR_DECL(expected,uint,16,4) [] = { 0x907, 0x908, 0x909, 0x90a };
>> +VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe7, 0xffffffe8 };
>> +VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
>> +VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
>> + 0x33, 0x33, 0x33, 0x33 };
>> +VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333
>> };
>> +VECT_VAR_DECL(expected,float,32,2) [] = { 4.172325e-08, 4.172325e-08 };
>> +VECT_VAR_DECL(expected,int,8,16) [] = { 0x5e, 0x5f, 0x60, 0x61,
>> + 0x62, 0x63, 0x64, 0x65,
>> + 0x66, 0x67, 0x68, 0x69,
>> + 0x6a, 0x6b, 0x6c, 0x6d };
>> +VECT_VAR_DECL(expected,int,16,8) [] = { 0xb9c, 0xb9d, 0xb9e, 0xb9f,
>> + 0xba0, 0xba1, 0xba2, 0xba3 };
>> +VECT_VAR_DECL(expected,int,32,4) [] = { 0x26e0, 0x26e1, 0x26e2, 0x26e3 };
>> +VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
>> + 0x3333333333333333 };
>> +VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
>> + 0xfc, 0xfd, 0xfe, 0xff,
>> + 0x0, 0x1, 0x2, 0x3,
>> + 0x4, 0x5, 0x6, 0x7 };
>> +VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff9, 0xfffa, 0xfffb, 0xfffc,
>> + 0xfffd, 0xfffe, 0xffff, 0x0 };
>> +VECT_VAR_DECL(expected,uint,32,4) [] = { 0xc, 0xd, 0xe, 0xf };
>> +VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
>> + 0x3333333333333333 };
>> +VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
>> + 0x33, 0x33, 0x33, 0x33,
>> + 0x33, 0x33, 0x33, 0x33,
>> + 0x33, 0x33, 0x33, 0x33 };
>> +VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
>> + 0x3333, 0x3333, 0x3333, 0x3333 };
>> +VECT_VAR_DECL(expected,float,32,4) [] = { 4.172325e-08, 4.172325e-08,
>> + 4.172325e-08, 4.172325e-08 };
>> +
>> +#define TEST_MSG "VABA/VABAQ"
>> +void exec_vaba (void)
>> +{
>> + /* Basic test: v4=vaba(v1,v2,v3), then store the result. */
>> +#define TEST_VABA(Q, T1, T2, W, N) \
>> + VECT_VAR(vector_res, T1, W, N) = \
>> + vaba##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
>> + VECT_VAR(vector2, T1, W, N), \
>> + VECT_VAR(vector3, T1, W, N)); \
>> + vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1,
>> W, N))
>> +
>> +#define DECL_VABA_VAR(VAR) \
>> + DECL_VARIABLE(VAR, int, 8, 8); \
>> + DECL_VARIABLE(VAR, int, 16, 4); \
>> + DECL_VARIABLE(VAR, int, 32, 2); \
>> + DECL_VARIABLE(VAR, uint, 8, 8); \
>> + DECL_VARIABLE(VAR, uint, 16, 4); \
>> + DECL_VARIABLE(VAR, uint, 32, 2); \
>> + DECL_VARIABLE(VAR, int, 8, 16); \
>> + DECL_VARIABLE(VAR, int, 16, 8); \
>> + DECL_VARIABLE(VAR, int, 32, 4); \
>> + DECL_VARIABLE(VAR, uint, 8, 16); \
>> + DECL_VARIABLE(VAR, uint, 16, 8); \
>> + DECL_VARIABLE(VAR, uint, 32, 4)
>> +
>> + DECL_VABA_VAR(vector1);
>> + DECL_VABA_VAR(vector2);
>> + DECL_VABA_VAR(vector3);
>> + DECL_VABA_VAR(vector_res);
>> +
>> + clean_results ();
>> +
>> + /* Initialize input "vector" from "buffer". */
>> + TEST_VLOAD(vector1, buffer, , int, s, 8, 8);
>> + TEST_VLOAD(vector1, buffer, , int, s, 16, 4);
>> + TEST_VLOAD(vector1, buffer, , int, s, 32, 2);
>> + TEST_VLOAD(vector1, buffer, , uint, u, 8, 8);
>> + TEST_VLOAD(vector1, buffer, , uint, u, 16, 4);
>> + TEST_VLOAD(vector1, buffer, , uint, u, 32, 2);
>> + TEST_VLOAD(vector1, buffer, q, int, s, 8, 16);
>> + TEST_VLOAD(vector1, buffer, q, int, s, 16, 8);
>> + TEST_VLOAD(vector1, buffer, q, int, s, 32, 4);
>> + TEST_VLOAD(vector1, buffer, q, uint, u, 8, 16);
>> + TEST_VLOAD(vector1, buffer, q, uint, u, 16, 8);
>> + TEST_VLOAD(vector1, buffer, q, uint, u, 32, 4);
>> +
>> + /* Choose init value arbitrarily. */
>> + TEST_VDUP(vector2, , int, s, 8, 8, 1);
>> + TEST_VDUP(vector2, , int, s, 16, 4, -13);
>> + TEST_VDUP(vector2, , int, s, 32, 2, 8);
>> + TEST_VDUP(vector2, , uint, u, 8, 8, 1);
>> + TEST_VDUP(vector2, , uint, u, 16, 4, 13);
>> + TEST_VDUP(vector2, , uint, u, 32, 2, 8);
>> + TEST_VDUP(vector2, q, int, s, 8, 16, 10);
>> + TEST_VDUP(vector2, q, int, s, 16, 8, -12);
>> + TEST_VDUP(vector2, q, int, s, 32, 4, 32);
>> + TEST_VDUP(vector2, q, uint, u, 8, 16, 10);
>> + TEST_VDUP(vector2, q, uint, u, 16, 8, 12);
>> + TEST_VDUP(vector2, q, uint, u, 32, 4, 32);
>> +
>> + /* Choose init value arbitrarily. */
>> + TEST_VDUP(vector3, , int, s, 8, 8, -5);
>> + TEST_VDUP(vector3, , int, s, 16, 4, 25);
>> + TEST_VDUP(vector3, , int, s, 32, 2, -40);
>> + TEST_VDUP(vector3, , uint, u, 8, 8, 100);
>> + TEST_VDUP(vector3, , uint, u, 16, 4, 2340);
>> + TEST_VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
>> + TEST_VDUP(vector3, q, int, s, 8, 16, -100);
>> + TEST_VDUP(vector3, q, int, s, 16, 8, -3000);
>> + TEST_VDUP(vector3, q, int, s, 32, 4, 10000);
>> + TEST_VDUP(vector3, q, uint, u, 8, 16, 2);
>> + TEST_VDUP(vector3, q, uint, u, 16, 8, 3);
>> + TEST_VDUP(vector3, q, uint, u, 32, 4, 4);
>> +
>> + /* Execute the tests. */
>> + TEST_VABA(, int, s, 8, 8);
>> + TEST_VABA(, int, s, 16, 4);
>> + TEST_VABA(, int, s, 32, 2);
>> + TEST_VABA(, uint, u, 8, 8);
>> + TEST_VABA(, uint, u, 16, 4);
>> + TEST_VABA(, uint, u, 32, 2);
>> + TEST_VABA(q, int, s, 8, 16);
>> + TEST_VABA(q, int, s, 16, 8);
>> + TEST_VABA(q, int, s, 32, 4);
>> + TEST_VABA(q, uint, u, 8, 16);
>> + TEST_VABA(q, uint, u, 16, 8);
>> + TEST_VABA(q, uint, u, 32, 4);
>> +
>> + check_results (TEST_MSG, "");
>> +}
>> +
>> +int main (void)
>> +{
>> + exec_vaba ();
>> + return 0;
>> +}
>> diff -rNup '--exclude=.git'
>> gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vld1.c
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vld1.c
>> --- gcc-fsf/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vld1.c
>> 1970-01-01 01:00:00.000000000 +0100
>> +++
>> gcc-fsf-neontests/gcc/testsuite/gcc.target/arm/neon-intrinsics/ref_vld1.c
>> 2013-05-09 00:39:00.351644429 +0200
>> @@ -0,0 +1,77 @@
>> +/* { dg-do run } */
>> +/* { dg-require-effective-target arm_neon_hw } */
>> +/* { dg-add-options arm_neon } */
>> +
>> +#include <arm_neon.h>
>> +#include "arm-neon-ref.h"
>> +#include "compute_ref_data.h"
>> +
>> +VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
>> + 0xf4, 0xf5, 0xf6, 0xf7 };
>> +VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
>> +VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
>> +VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
>> +VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
>> + 0xf4, 0xf5, 0xf6, 0xf7 };
>> +VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3
>> };
>> +VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
>> +VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
>> +VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
>> + 0xf4, 0xf5, 0xf6, 0xf7 };
>> +VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3
>> };
>> +VECT_VAR_DECL(expected,float,32,2) [] = { -16, -15 };
>> +VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
>> + 0xf4, 0xf5, 0xf6, 0xf7,
>> + 0xf8, 0xf9, 0xfa, 0xfb,
>> + 0xfc, 0xfd, 0xfe, 0xff };
>> +VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
>> + 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
>> +VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
>> + 0xfffffff2, 0xfffffff3 };
>> +VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0,
>> + 0xfffffffffffffff1 };
>> +VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
>> + 0xf4, 0xf5, 0xf6, 0xf7,
>> + 0xf8, 0xf9, 0xfa, 0xfb,
>> + 0xfc, 0xfd, 0xfe, 0xff };
>> +VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2,
>> + 0xfff3, 0xfff4, 0xfff5,
>> + 0xfff6, 0xfff7 };
>> +VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
>> + 0xfffffff2, 0xfffffff3 };
>> +VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0,
>> + 0xfffffffffffffff1 };
>> +VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
>> + 0xf4, 0xf5, 0xf6, 0xf7,
>> + 0xf8, 0xf9, 0xfa, 0xfb,
>> + 0xfc, 0xfd, 0xfe, 0xff };
>> +VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
>> + 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
>> +VECT_VAR_DECL(expected,float,32,4) [] = { -16, -15, -14, -13 };
>> +
>> +#define TEST_MSG "VLD1/VLD1Q"
>> +void exec_vld1 (void)
>> +{
>> + /* Basic test vec=vld1(buffer); then store vec: vst1(result, vector).
>> */
>> + /* This test actually tests vdl1 and vst1 at the same time. */
>> +#define TEST_VLD1(VAR, BUF, Q, T1, T2, W, N) \
>> + VECT_VAR(VAR, T1, W, N) = vld1##Q##_##T2##W(VECT_VAR(BUF, T1, W, N)); \
>> + vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(VAR, T1, W, N))
>> +
>> + DECL_VARIABLE_ALL_VARIANTS(vector);
>> +
>> + clean_results ();
>> +
>> + TEST_MACRO_ALL_VARIANTS_2_5(TEST_VLD1, vector, buffer);
>> +
>> + TEST_VLD1(vector, buffer, , float, f, 32, 2);
>> + TEST_VLD1(vector, buffer, q, float, f, 32, 4);
>> +
>> + check_results (TEST_MSG, "");
>> +}
>> +
>> +int main (void)
>> +{
>> + exec_vld1 ();
>> + return 0;
>> +}
>>
>
>
