[libclc] r312403 - relational: Implement shuffle builtin
Aaron Watry via cfe-commits
cfe-commits at lists.llvm.org
Fri Sep 1 19:23:26 PDT 2017
Author: awatry
Date: Fri Sep 1 19:23:26 2017
New Revision: 312403
URL: http://llvm.org/viewvc/llvm-project?rev=312403&view=rev
Log:
relational: Implement shuffle builtin
This was added in CL 1.1
Tested with a Radeon HD 7850 (Pitcairn) using the CL CTS via:
test_conformance/relationals/test_relationals shuffle_built_in
v2: Add half-precision support to shuffle when available.
Move to misc/ and add section 6.12.12 to clc.h
Signed-off-by: Aaron Watry <awatry at gmail.com>
Reviewed-by: Jan Vesely <jan.vesely at rutgers.edu>
Added:
libclc/trunk/generic/include/clc/misc/
libclc/trunk/generic/include/clc/misc/shuffle.h
libclc/trunk/generic/lib/misc/
libclc/trunk/generic/lib/misc/shuffle.cl
Modified:
libclc/trunk/generic/include/clc/clc.h
libclc/trunk/generic/lib/SOURCES
Modified: libclc/trunk/generic/include/clc/clc.h
URL: http://llvm.org/viewvc/llvm-project/libclc/trunk/generic/include/clc/clc.h?rev=312403&r1=312402&r2=312403&view=diff
==============================================================================
--- libclc/trunk/generic/include/clc/clc.h (original)
+++ libclc/trunk/generic/include/clc/clc.h Fri Sep 1 19:23:26 2017
@@ -237,6 +237,9 @@
/* 6.11.13 Image Read and Write Functions */
+/* 6.12.12 Miscellaneous Vector Functions */
+#include <clc/misc/shuffle.h>
+
#include <clc/image/image_defines.h>
#include <clc/image/image.h>
Added: libclc/trunk/generic/include/clc/misc/shuffle.h
URL: http://llvm.org/viewvc/llvm-project/libclc/trunk/generic/include/clc/misc/shuffle.h?rev=312403&view=auto
==============================================================================
--- libclc/trunk/generic/include/clc/misc/shuffle.h (added)
+++ libclc/trunk/generic/include/clc/misc/shuffle.h Fri Sep 1 19:23:26 2017
@@ -0,0 +1,47 @@
+//===-- generic/include/clc/misc/shuffle.h ------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under both the University of Illinois Open Source
+// License and the MIT license. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#define _CLC_SHUFFLE_DECL(TYPE, MASKTYPE, RETTYPE) \
+ _CLC_OVERLOAD _CLC_DECL RETTYPE shuffle(TYPE x, MASKTYPE mask);
+
+//Return type is same base type as the input type, with the same vector size as the mask.
+//Elements in the mask must be the same size (number of bits) as the input value.
+//E.g. char8 ret = shuffle(char2 x, uchar8 mask);
+
+#define _CLC_VECTOR_SHUFFLE_MASKSIZE(INBASE, INTYPE, MASKTYPE) \
+ _CLC_SHUFFLE_DECL(INTYPE, MASKTYPE##2, INBASE##2) \
+ _CLC_SHUFFLE_DECL(INTYPE, MASKTYPE##4, INBASE##4) \
+ _CLC_SHUFFLE_DECL(INTYPE, MASKTYPE##8, INBASE##8) \
+ _CLC_SHUFFLE_DECL(INTYPE, MASKTYPE##16, INBASE##16) \
+
+#define _CLC_VECTOR_SHUFFLE_INSIZE(TYPE, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, TYPE##2, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, TYPE##4, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, TYPE##8, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, TYPE##16, MASKTYPE) \
+
+_CLC_VECTOR_SHUFFLE_INSIZE(char, uchar)
+_CLC_VECTOR_SHUFFLE_INSIZE(short, ushort)
+_CLC_VECTOR_SHUFFLE_INSIZE(int, uint)
+_CLC_VECTOR_SHUFFLE_INSIZE(long, ulong)
+_CLC_VECTOR_SHUFFLE_INSIZE(uchar, uchar)
+_CLC_VECTOR_SHUFFLE_INSIZE(ushort, ushort)
+_CLC_VECTOR_SHUFFLE_INSIZE(uint, uint)
+_CLC_VECTOR_SHUFFLE_INSIZE(ulong, ulong)
+_CLC_VECTOR_SHUFFLE_INSIZE(float, uint)
+#ifdef cl_khr_fp64
+_CLC_VECTOR_SHUFFLE_INSIZE(double, ulong)
+#endif
+#ifdef cl_khr_fp16
+_CLC_VECTOR_SHUFFLE_INSIZE(half, ushort)
+#endif
+
+#undef _CLC_SHUFFLE_DECL
+#undef _CLC_VECTOR_SHUFFLE_MASKSIZE
+#undef _CLC_VECTOR_SHUFFLE_INSIZE
Modified: libclc/trunk/generic/lib/SOURCES
URL: http://llvm.org/viewvc/llvm-project/libclc/trunk/generic/lib/SOURCES?rev=312403&r1=312402&r2=312403&view=diff
==============================================================================
--- libclc/trunk/generic/lib/SOURCES (original)
+++ libclc/trunk/generic/lib/SOURCES Fri Sep 1 19:23:26 2017
@@ -123,6 +123,7 @@ math/sqrt.cl
math/tan.cl
math/tanh.cl
math/tgamma.cl
+misc/shuffle.cl
relational/all.cl
relational/any.cl
relational/bitselect.cl
@@ -139,6 +140,7 @@ relational/isnormal.cl
relational/isnotequal.cl
relational/isordered.cl
relational/isunordered.cl
+relational/shuffle2.cl
relational/signbit.cl
shared/clamp.cl
shared/max.cl
Added: libclc/trunk/generic/lib/misc/shuffle.cl
URL: http://llvm.org/viewvc/llvm-project/libclc/trunk/generic/lib/misc/shuffle.cl?rev=312403&view=auto
==============================================================================
--- libclc/trunk/generic/lib/misc/shuffle.cl (added)
+++ libclc/trunk/generic/lib/misc/shuffle.cl Fri Sep 1 19:23:26 2017
@@ -0,0 +1,157 @@
+//===-- generic/lib/misc/shuffle.cl ------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under both the University of Illinois Open Source
+// License and the MIT license. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include <clc/clc.h>
+
+#define _CLC_ELEMENT_CASES2(VAR) \
+ case 0: return VAR.s0; \
+ case 1: return VAR.s1;
+
+#define _CLC_ELEMENT_CASES4(VAR) \
+ _CLC_ELEMENT_CASES2(VAR) \
+ case 2: return VAR.s2; \
+ case 3: return VAR.s3;
+
+#define _CLC_ELEMENT_CASES8(VAR) \
+ _CLC_ELEMENT_CASES4(VAR) \
+ case 4: return VAR.s4; \
+ case 5: return VAR.s5; \
+ case 6: return VAR.s6; \
+ case 7: return VAR.s7;
+
+#define _CLC_ELEMENT_CASES16(VAR) \
+ _CLC_ELEMENT_CASES8(VAR) \
+ case 8: return VAR.s8; \
+ case 9: return VAR.s9; \
+ case 10: return VAR.sA; \
+ case 11: return VAR.sB; \
+ case 12: return VAR.sC; \
+ case 13: return VAR.sD; \
+ case 14: return VAR.sE; \
+ case 15: return VAR.sF;
+
+#define _CLC_GET_ELEMENT_DEFINE(ARGTYPE, ARGSIZE, IDXTYPE) \
+ inline ARGTYPE __clc_get_el_##ARGTYPE##ARGSIZE##_##IDXTYPE(ARGTYPE##ARGSIZE x, IDXTYPE idx) {\
+ switch (idx){ \
+ _CLC_ELEMENT_CASES##ARGSIZE(x) \
+ default: return 0; \
+ } \
+ } \
+
+#define _CLC_SHUFFLE_SET_ONE_ELEMENT(ARGTYPE, ARGSIZE, INDEX, MASKTYPE) \
+ ret_val.s##INDEX = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s##INDEX); \
+
+#define _CLC_SHUFFLE_SET_2_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ ret_val.s0 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s0); \
+ ret_val.s1 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s1);
+
+#define _CLC_SHUFFLE_SET_4_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_SHUFFLE_SET_2_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ ret_val.s2 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s2); \
+ ret_val.s3 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s3);
+
+#define _CLC_SHUFFLE_SET_8_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_SHUFFLE_SET_4_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ ret_val.s4 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s4); \
+ ret_val.s5 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s5); \
+ ret_val.s6 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s6); \
+ ret_val.s7 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s7);
+
+#define _CLC_SHUFFLE_SET_16_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_SHUFFLE_SET_8_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ ret_val.s8 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s8); \
+ ret_val.s9 = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.s9); \
+ ret_val.sA = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.sA); \
+ ret_val.sB = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.sB); \
+ ret_val.sC = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.sC); \
+ ret_val.sD = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.sD); \
+ ret_val.sE = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.sE); \
+ ret_val.sF = __clc_get_el_##ARGTYPE##ARGSIZE##_##MASKTYPE(x, mask.sF); \
+
+#define _CLC_SHUFFLE_DEFINE2(ARGTYPE, ARGSIZE, MASKTYPE) \
+_CLC_DEF _CLC_OVERLOAD ARGTYPE##2 shuffle(ARGTYPE##ARGSIZE x, MASKTYPE##2 mask){ \
+ ARGTYPE##2 ret_val; \
+ mask &= (MASKTYPE##2)(ARGSIZE-1); \
+ _CLC_SHUFFLE_SET_2_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ return ret_val; \
+}
+
+#define _CLC_SHUFFLE_DEFINE4(ARGTYPE, ARGSIZE, MASKTYPE) \
+_CLC_DEF _CLC_OVERLOAD ARGTYPE##4 shuffle(ARGTYPE##ARGSIZE x, MASKTYPE##4 mask){ \
+ ARGTYPE##4 ret_val; \
+ mask &= (MASKTYPE##4)(ARGSIZE-1); \
+ _CLC_SHUFFLE_SET_4_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ return ret_val; \
+}
+
+#define _CLC_SHUFFLE_DEFINE8(ARGTYPE, ARGSIZE, MASKTYPE) \
+_CLC_DEF _CLC_OVERLOAD ARGTYPE##8 shuffle(ARGTYPE##ARGSIZE x, MASKTYPE##8 mask){ \
+ ARGTYPE##8 ret_val; \
+ mask &= (MASKTYPE##8)(ARGSIZE-1); \
+ _CLC_SHUFFLE_SET_8_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ return ret_val; \
+}
+
+#define _CLC_SHUFFLE_DEFINE16(ARGTYPE, ARGSIZE, MASKTYPE) \
+_CLC_DEF _CLC_OVERLOAD ARGTYPE##16 shuffle(ARGTYPE##ARGSIZE x, MASKTYPE##16 mask){ \
+ ARGTYPE##16 ret_val; \
+ mask &= (MASKTYPE##16)(ARGSIZE-1); \
+ _CLC_SHUFFLE_SET_16_ELEMENTS(ARGTYPE, ARGSIZE, MASKTYPE) \
+ return ret_val; \
+}
+
+#define _CLC_VECTOR_SHUFFLE_MASKSIZE(INTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_GET_ELEMENT_DEFINE(INTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_SHUFFLE_DEFINE2(INTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_SHUFFLE_DEFINE4(INTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_SHUFFLE_DEFINE8(INTYPE, ARGSIZE, MASKTYPE) \
+ _CLC_SHUFFLE_DEFINE16(INTYPE, ARGSIZE, MASKTYPE) \
+
+#define _CLC_VECTOR_SHUFFLE_INSIZE(TYPE, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, 2, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, 4, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, 8, MASKTYPE) \
+ _CLC_VECTOR_SHUFFLE_MASKSIZE(TYPE, 16, MASKTYPE) \
+
+
+
+_CLC_VECTOR_SHUFFLE_INSIZE(char, uchar)
+_CLC_VECTOR_SHUFFLE_INSIZE(short, ushort)
+_CLC_VECTOR_SHUFFLE_INSIZE(int, uint)
+_CLC_VECTOR_SHUFFLE_INSIZE(long, ulong)
+_CLC_VECTOR_SHUFFLE_INSIZE(uchar, uchar)
+_CLC_VECTOR_SHUFFLE_INSIZE(ushort, ushort)
+_CLC_VECTOR_SHUFFLE_INSIZE(uint, uint)
+_CLC_VECTOR_SHUFFLE_INSIZE(ulong, ulong)
+_CLC_VECTOR_SHUFFLE_INSIZE(float, uint)
+#ifdef cl_khr_fp64
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+_CLC_VECTOR_SHUFFLE_INSIZE(double, ulong)
+#endif
+#ifdef cl_khr_fp16
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+_CLC_VECTOR_SHUFFLE_INSIZE(half, ushort)
+#endif
+
+#undef _CLC_ELEMENT_CASES2
+#undef _CLC_ELEMENT_CASES4
+#undef _CLC_ELEMENT_CASES8
+#undef _CLC_ELEMENT_CASES16
+#undef _CLC_GET_ELEMENT_DEFINE
+#undef _CLC_SHUFFLE_SET_ONE_ELEMENT
+#undef _CLC_SHUFFLE_SET_2_ELEMENTS
+#undef _CLC_SHUFFLE_SET_4_ELEMENTS
+#undef _CLC_SHUFFLE_SET_8_ELEMENTS
+#undef _CLC_SHUFFLE_SET_16_ELEMENTS
+#undef _CLC_SHUFFLE_DEFINE2
+#undef _CLC_SHUFFLE_DEFINE4
+#undef _CLC_SHUFFLE_DEFINE8
+#undef _CLC_SHUFFLE_DEFINE16
+#undef _CLC_VECTOR_SHUFFLE_MASKSIZE
+#undef _CLC_VECTOR_SHUFFLE_INSIZE
More information about the cfe-commits
mailing list