[Libclc-dev] [PATCH v2 3/3] Implement vload_half{, n} and vload(half)
Aaron Watry via Libclc-dev
libclc-dev at lists.llvm.org
Thu Sep 14 07:28:40 PDT 2017
Just curious,
Would you be interested in implementing vloada_halfN and vstorea_halfN
as well? I was just running through some CTS tests, and it failed on
an implicit declaration of those functions.
I believe that the only real difference is that vloada_halfN requires
that the pointers be aligned to sizeof(halfN) instead of 16-bit
alignment, with 64-bit alignment for half3's (4*sizeof(half)).
If not, I can take a look at this when I've got time (a.k.a. could be
tomorrow, could be next year).
--Aaron
On Thu, Sep 7, 2017 at 2:47 PM, Jan Vesely via Libclc-dev
<libclc-dev at lists.llvm.org> wrote:
> On Fri, 2017-09-01 at 20:31 -0400, Jan Vesely wrote:
>> v2: add vload(half) as well
>> make helpers amdgpu specific (NVPTX uses different private AS numbering)
>> use clang builtin on clang >= 6
>>
>> Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
>> ---
>> needs [PATCH 1/3] Add halfN types and enable fp16 when generating
>> builtin declarations from Aaron
>> clang builtins require https://reviews.llvm.org/D37231
>
> just FYI, the clang patch is now merged as r312742.
>
> Jan
>
>> Passes vload_half piglits on turks (clang-6)
>> Passes vload_half and vload(half) piglits on carrizo (clang-5)
>>
>> amdgpu/lib/SOURCES_4.0 | 1 +
>> amdgpu/lib/SOURCES_5.0 | 1 +
>> amdgpu/lib/shared/vload_half_helpers.ll | 23 +++++++++++++
>> generic/include/clc/shared/vload.h | 55 +++++++++++++++++++-----------
>> generic/lib/shared/vload.cl | 59 +++++++++++++++++++++++++++++++++
>> generic/lib/shared/vload_half.inc | 13 ++++++++
>> 6 files changed, 132 insertions(+), 20 deletions(-)
>> create mode 100644 amdgpu/lib/shared/vload_half_helpers.ll
>> create mode 100644 generic/lib/shared/vload_half.inc
>>
>> diff --git a/amdgpu/lib/SOURCES_4.0 b/amdgpu/lib/SOURCES_4.0
>> index 5851798..69c5e5c 100644
>> --- a/amdgpu/lib/SOURCES_4.0
>> +++ b/amdgpu/lib/SOURCES_4.0
>> @@ -1 +1,2 @@
>> +shared/vload_half_helpers.ll
>> shared/vstore_half_helpers.ll
>> diff --git a/amdgpu/lib/SOURCES_5.0 b/amdgpu/lib/SOURCES_5.0
>> index 5851798..69c5e5c 100644
>> --- a/amdgpu/lib/SOURCES_5.0
>> +++ b/amdgpu/lib/SOURCES_5.0
>> @@ -1 +1,2 @@
>> +shared/vload_half_helpers.ll
>> shared/vstore_half_helpers.ll
>> diff --git a/amdgpu/lib/shared/vload_half_helpers.ll b/amdgpu/lib/shared/vload_half_helpers.ll
>> new file mode 100644
>> index 0000000..b8c905a
>> --- /dev/null
>> +++ b/amdgpu/lib/shared/vload_half_helpers.ll
>> @@ -0,0 +1,23 @@
>> +define float @__clc_vload_half_float_helper__private(half addrspace(0)* nocapture %ptr) nounwind alwaysinline {
>> + %data = load half, half addrspace(0)* %ptr
>> + %res = fpext half %data to float
>> + ret float %res
>> +}
>> +
>> +define float @__clc_vload_half_float_helper__global(half addrspace(1)* nocapture %ptr) nounwind alwaysinline {
>> + %data = load half, half addrspace(1)* %ptr
>> + %res = fpext half %data to float
>> + ret float %res
>> +}
>> +
>> +define float @__clc_vload_half_float_helper__local(half addrspace(3)* nocapture %ptr) nounwind alwaysinline {
>> + %data = load half, half addrspace(3)* %ptr
>> + %res = fpext half %data to float
>> + ret float %res
>> +}
>> +
>> +define float @__clc_vload_half_float_helper__constant(half addrspace(2)* nocapture %ptr) nounwind alwaysinline {
>> + %data = load half, half addrspace(2)* %ptr
>> + %res = fpext half %data to float
>> + ret float %res
>> +}
>> diff --git a/generic/include/clc/shared/vload.h b/generic/include/clc/shared/vload.h
>> index 93d0750..8c262dd 100644
>> --- a/generic/include/clc/shared/vload.h
>> +++ b/generic/include/clc/shared/vload.h
>> @@ -1,18 +1,21 @@
>> -#define _CLC_VLOAD_DECL(PRIM_TYPE, VEC_TYPE, WIDTH, ADDR_SPACE) \
>> - _CLC_OVERLOAD _CLC_DECL VEC_TYPE vload##WIDTH(size_t offset, const ADDR_SPACE PRIM_TYPE *x);
>> +#define _CLC_VLOAD_DECL(SUFFIX, MEM_TYPE, VEC_TYPE, WIDTH, ADDR_SPACE) \
>> + _CLC_OVERLOAD _CLC_DECL VEC_TYPE vload##SUFFIX##WIDTH(size_t offset, const ADDR_SPACE MEM_TYPE *x);
>>
>> -#define _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, ADDR_SPACE) \
>> - _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##2, 2, ADDR_SPACE) \
>> - _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##3, 3, ADDR_SPACE) \
>> - _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##4, 4, ADDR_SPACE) \
>> - _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##8, 8, ADDR_SPACE) \
>> - _CLC_VLOAD_DECL(PRIM_TYPE, PRIM_TYPE##16, 16, ADDR_SPACE)
>> +#define _CLC_VECTOR_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE, ADDR_SPACE) \
>> + _CLC_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE##2, 2, ADDR_SPACE) \
>> + _CLC_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE##3, 3, ADDR_SPACE) \
>> + _CLC_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE##4, 4, ADDR_SPACE) \
>> + _CLC_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE##8, 8, ADDR_SPACE) \
>> + _CLC_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE##16, 16, ADDR_SPACE)
>> +
>> +#define _CLC_VECTOR_VLOAD_PRIM3(SUFFIX, MEM_TYPE, PRIM_TYPE) \
>> + _CLC_VECTOR_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE, __private) \
>> + _CLC_VECTOR_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE, __local) \
>> + _CLC_VECTOR_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE, __constant) \
>> + _CLC_VECTOR_VLOAD_DECL(SUFFIX, MEM_TYPE, PRIM_TYPE, __global) \
>>
>> #define _CLC_VECTOR_VLOAD_PRIM1(PRIM_TYPE) \
>> - _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __private) \
>> - _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __local) \
>> - _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __constant) \
>> - _CLC_VECTOR_VLOAD_DECL(PRIM_TYPE, __global) \
>> + _CLC_VECTOR_VLOAD_PRIM3(, PRIM_TYPE, PRIM_TYPE) \
>>
>> #define _CLC_VECTOR_VLOAD_PRIM() \
>> _CLC_VECTOR_VLOAD_PRIM1(char) \
>> @@ -24,14 +27,26 @@
>> _CLC_VECTOR_VLOAD_PRIM1(long) \
>> _CLC_VECTOR_VLOAD_PRIM1(ulong) \
>> _CLC_VECTOR_VLOAD_PRIM1(float) \
>> -
>> + _CLC_VECTOR_VLOAD_PRIM3(_half, half, float)
>> +
>> #ifdef cl_khr_fp64
>> -#define _CLC_VECTOR_VLOAD() \
>> - _CLC_VECTOR_VLOAD_PRIM1(double) \
>> - _CLC_VECTOR_VLOAD_PRIM()
>> -#else
>> -#define _CLC_VECTOR_VLOAD() \
>> - _CLC_VECTOR_VLOAD_PRIM()
>> +#pragma OPENCL EXTENSION cl_khr_fp64: enable
>> + _CLC_VECTOR_VLOAD_PRIM1(double)
>> #endif
>> +#ifdef cl_khr_fp16
>> +#pragma OPENCL EXTENSION cl_khr_fp16: enable
>> + _CLC_VECTOR_VLOAD_PRIM1(half)
>> +#endif
>> +
>> +_CLC_VECTOR_VLOAD_PRIM()
>> +// Plain vload_half also needs to be declared
>> +_CLC_VLOAD_DECL(_half, half, float, , __constant)
>> +_CLC_VLOAD_DECL(_half, half, float, , __global)
>> +_CLC_VLOAD_DECL(_half, half, float, , __local)
>> +_CLC_VLOAD_DECL(_half, half, float, , __private)
>>
>> -_CLC_VECTOR_VLOAD()
>> +#undef _CLC_VLOAD_DECL
>> +#undef _CLC_VECTOR_VLOAD_DECL
>> +#undef _CLC_VECTOR_VLOAD_PRIM3
>> +#undef _CLC_VECTOR_VLOAD_PRIM1
>> +#undef _CLC_VECTOR_VLOAD_PRIM
>> diff --git a/generic/lib/shared/vload.cl b/generic/lib/shared/vload.cl
>> index 8897200..0892270 100644
>> --- a/generic/lib/shared/vload.cl
>> +++ b/generic/lib/shared/vload.cl
>> @@ -50,3 +50,62 @@ VLOAD_TYPES()
>> #pragma OPENCL EXTENSION cl_khr_fp64 : enable
>> VLOAD_ADDR_SPACES(double)
>> #endif
>> +#ifdef cl_khr_fp16
>> +#pragma OPENCL EXTENSION cl_khr_fp16 : enable
>> + VLOAD_ADDR_SPACES(half)
>> +#endif
>> +
>> +/* vload_half are legal even without cl_khr_fp16 */
>> +/* no vload_half for double */
>> +#if __clang_major__ < 6
>> +float __clc_vload_half_float_helper__constant(const __constant half *);
>> +float __clc_vload_half_float_helper__global(const __global half *);
>> +float __clc_vload_half_float_helper__local(const __local half *);
>> +float __clc_vload_half_float_helper__private(const __private half *);
>> +
>> +#define VEC_LOAD1(val, AS) val = __clc_vload_half_float_helper##AS (&mem[offset++]);
>> +#else
>> +#define VEC_LOAD1(val, AS) val = __builtin_load_halff(&mem[offset++]);
>> +#endif
>> +
>> +#define VEC_LOAD2(val, AS) \
>> + VEC_LOAD1(val.lo, AS) \
>> + VEC_LOAD1(val.hi, AS)
>> +#define VEC_LOAD3(val, AS) \
>> + VEC_LOAD1(val.s0, AS) \
>> + VEC_LOAD1(val.s1, AS) \
>> + VEC_LOAD1(val.s2, AS)
>> +#define VEC_LOAD4(val, AS) \
>> + VEC_LOAD2(val.lo, AS) \
>> + VEC_LOAD2(val.hi, AS)
>> +#define VEC_LOAD8(val, AS) \
>> + VEC_LOAD4(val.lo, AS) \
>> + VEC_LOAD4(val.hi, AS)
>> +#define VEC_LOAD16(val, AS) \
>> + VEC_LOAD8(val.lo, AS) \
>> + VEC_LOAD8(val.hi, AS)
>> +
>> +#define __FUNC(SUFFIX, VEC_SIZE, TYPE, AS) \
>> + _CLC_OVERLOAD _CLC_DEF TYPE vload_half##SUFFIX(size_t offset, const AS half *mem) { \
>> + offset *= VEC_SIZE; \
>> + TYPE __tmp; \
>> + VEC_LOAD##VEC_SIZE(__tmp, AS) \
>> + return __tmp; \
>> + }
>> +
>> +#define FUNC(SUFFIX, VEC_SIZE, TYPE, AS) __FUNC(SUFFIX, VEC_SIZE, TYPE, AS)
>> +
>> +#define __CLC_BODY "vload_half.inc"
>> +#include <clc/math/gentype.inc>
>> +#undef __CLC_BODY
>> +#undef FUNC
>> +#undef __FUNC
>> +#undef VEC_LOAD16
>> +#undef VEC_LOAD8
>> +#undef VEC_LOAD4
>> +#undef VEC_LOAD3
>> +#undef VEC_LOAD2
>> +#undef VEC_LOAD1
>> +#undef VLOAD_TYPES
>> +#undef VLOAD_ADDR_SPACES
>> +#undef VLOAD_VECTORIZE
>> diff --git a/generic/lib/shared/vload_half.inc b/generic/lib/shared/vload_half.inc
>> new file mode 100644
>> index 0000000..00dae8a
>> --- /dev/null
>> +++ b/generic/lib/shared/vload_half.inc
>> @@ -0,0 +1,13 @@
>> +#if __CLC_FPSIZE == 32
>> +#ifdef __CLC_VECSIZE
>> + FUNC(__CLC_VECSIZE, __CLC_VECSIZE, __CLC_GENTYPE, __private);
>> + FUNC(__CLC_VECSIZE, __CLC_VECSIZE, __CLC_GENTYPE, __local);
>> + FUNC(__CLC_VECSIZE, __CLC_VECSIZE, __CLC_GENTYPE, __global);
>> + FUNC(__CLC_VECSIZE, __CLC_VECSIZE, __CLC_GENTYPE, __constant);
>> +#else
>> + FUNC(, 1, __CLC_GENTYPE, __private);
>> + FUNC(, 1, __CLC_GENTYPE, __local);
>> + FUNC(, 1, __CLC_GENTYPE, __global);
>> + FUNC(, 1, __CLC_GENTYPE, __constant);
>> +#endif
>> +#endif
>
> _______________________________________________
> Libclc-dev mailing list
> Libclc-dev at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/libclc-dev
>
More information about the Libclc-dev
mailing list