diff options
author | Aaron Watry <awatry@gmail.com> | 2013-05-29 10:40:27 -0500 |
---|---|---|
committer | Aaron Watry <awatry@gmail.com> | 2013-05-29 10:40:27 -0500 |
commit | c2df68f099bdd7633e0d2c711a64473fb9a4ed09 (patch) | |
tree | ee8f017a99aefb7e3819c4ce18de4cad345a5fba | |
parent | 38982ace51e1e1892c2357530e4e733ce547647d (diff) | |
parent | 265b4637effe3a4dbab56690e7a9e77b5bd6c3ce (diff) |
Merge branch 'master' of git://people.freedesktop.org/~tstellar/libclc
Conflicts:
generic/lib/SOURCES
generic/lib/shared/vload.cl
generic/lib/shared/vstore.cl
-rw-r--r-- | generic/lib/SOURCES | 4 | ||||
-rw-r--r-- | generic/lib/shared/vload.cl | 54 | ||||
-rw-r--r-- | generic/lib/shared/vload_if.ll | 60 | ||||
-rw-r--r-- | generic/lib/shared/vload_impl.ll | 49 | ||||
-rw-r--r-- | generic/lib/shared/vstore.cl | 58 | ||||
-rw-r--r-- | generic/lib/shared/vstore_if.ll | 59 | ||||
-rw-r--r-- | generic/lib/shared/vstore_impl.ll | 50 |
7 files changed, 330 insertions, 4 deletions
diff --git a/generic/lib/SOURCES b/generic/lib/SOURCES index ccbb59a..c2da3d7 100644 --- a/generic/lib/SOURCES +++ b/generic/lib/SOURCES @@ -26,6 +26,10 @@ shared/clamp.cl shared/max.cl shared/min.cl shared/vload.cl +shared/vload_if.ll +shared/vload_impl.ll shared/vstore.cl +shared/vstore_if.ll +shared/vstore_impl.ll workitem/get_global_id.cl workitem/get_global_size.cl diff --git a/generic/lib/shared/vload.cl b/generic/lib/shared/vload.cl index 24d8240..e47aa2e 100644 --- a/generic/lib/shared/vload.cl +++ b/generic/lib/shared/vload.cl @@ -27,13 +27,12 @@ VLOAD_VECTORIZE(SCALAR_GENTYPE, __constant) \ VLOAD_VECTORIZE(SCALAR_GENTYPE, __global) \ +//int/uint are special... see below #define VLOAD_TYPES() \ VLOAD_ADDR_SPACES(char) \ VLOAD_ADDR_SPACES(uchar) \ VLOAD_ADDR_SPACES(short) \ VLOAD_ADDR_SPACES(ushort) \ - VLOAD_ADDR_SPACES(int) \ - VLOAD_ADDR_SPACES(uint) \ VLOAD_ADDR_SPACES(long) \ VLOAD_ADDR_SPACES(ulong) \ VLOAD_ADDR_SPACES(float) \ @@ -45,3 +44,54 @@ VLOAD_TYPES() VLOAD_ADDR_SPACES(double) #endif +VLOAD_VECTORIZE(int, __private) +VLOAD_VECTORIZE(int, __local) +VLOAD_VECTORIZE(int, __constant) +VLOAD_VECTORIZE(uint, __private) +VLOAD_VECTORIZE(uint, __local) +VLOAD_VECTORIZE(uint, __constant) + +_CLC_OVERLOAD _CLC_DEF int2 vload2(size_t offset, const global int *x) { + return (int2)(x[offset] , x[offset+1]); +} +_CLC_OVERLOAD _CLC_DEF int3 vload3(size_t offset, const global int *x) { + return (int3)(vload2(offset, x), x[offset+2]); +} +_CLC_OVERLOAD _CLC_DEF uint2 vload2(size_t offset, const global uint *x) { + return (uint2)(x[offset] , x[offset+1]); +} +_CLC_OVERLOAD _CLC_DEF uint3 vload3(size_t offset, const global uint *x) { + return (uint3)(vload2(offset, x), x[offset+2]); +} + +/*Note: It is known that R600 doesn't support load <2 x ?> and <3 x ?>... so + * they aren't actually overridden here + */ +_CLC_DECL int4 __clc_vload4_int__global(size_t offset, const __global int *); +_CLC_DECL int8 __clc_vload8_int__global(size_t offset, const __global int *); +_CLC_DECL int16 __clc_vload16_int__global(size_t offset, const __global int *); + +_CLC_OVERLOAD _CLC_DEF int4 vload4(size_t offset, const global int *x) { + return __clc_vload4_int__global(offset, x); +} +_CLC_OVERLOAD _CLC_DEF int8 vload8(size_t offset, const global int *x) { + return __clc_vload8_int__global(offset, x); +} +_CLC_OVERLOAD _CLC_DEF int16 vload16(size_t offset, const global int *x) { + return __clc_vload16_int__global(offset, x); +} + +_CLC_DECL uint4 __clc_vload4_uint__global(size_t offset, const __global uint *); +_CLC_DECL uint8 __clc_vload8_uint__global(size_t offset, const __global uint *); +_CLC_DECL uint16 __clc_vload16_uint__global(size_t offset, const __global uint *); + +_CLC_OVERLOAD _CLC_DEF uint4 vload4(size_t offset, const global uint *x) { + return __clc_vload4_uint__global(offset, x); +} +_CLC_OVERLOAD _CLC_DEF uint8 vload8(size_t offset, const global uint *x) { + return __clc_vload8_uint__global(offset, x); +} +_CLC_OVERLOAD _CLC_DEF uint16 vload16(size_t offset, const global uint *x) { + return __clc_vload16_uint__global(offset, x); +} + diff --git a/generic/lib/shared/vload_if.ll b/generic/lib/shared/vload_if.ll new file mode 100644 index 0000000..2634d37 --- /dev/null +++ b/generic/lib/shared/vload_if.ll @@ -0,0 +1,60 @@ +;Start int global vload + +declare <2 x i32> @__clc_vload2_impl_i32__global(i32 %x, i32 %y) +declare <3 x i32> @__clc_vload3_impl_i32__global(i32 %x, i32 %y) +declare <4 x i32> @__clc_vload4_impl_i32__global(i32 %x, i32 %y) +declare <8 x i32> @__clc_vload8_impl_i32__global(i32 %x, i32 %y) +declare <16 x i32> @__clc_vload16_impl_i32__global(i32 %x, i32 %y) + +define <2 x i32> @__clc_vload2_int__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <2 x i32> @__clc_vload2_impl_i32__global(i32 %x, i32 %y) + ret <2 x i32> %call +} + +define <3 x i32> @__clc_vload3_int__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <3 x i32> @__clc_vload3_impl_i32__global(i32 %x, i32 %y) + ret <3 x i32> %call +} + +define <4 x i32> @__clc_vload4_int__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <4 x i32> @__clc_vload4_impl_i32__global(i32 %x, i32 %y) + ret <4 x i32> %call +} + +define <8 x i32> @__clc_vload8_int__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <8 x i32> @__clc_vload8_impl_i32__global(i32 %x, i32 %y) + ret <8 x i32> %call +} + +define <16 x i32> @__clc_vload16_int__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <16 x i32> @__clc_vload16_impl_i32__global(i32 %x, i32 %y) + ret <16 x i32> %call +} + + +;Start uint global vload + +define <2 x i32> @__clc_vload2_uint__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <2 x i32> @__clc_vload2_impl_i32__global(i32 %x, i32 %y) + ret <2 x i32> %call +} + +define <3 x i32> @__clc_vload3_uint__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <3 x i32> @__clc_vload3_impl_i32__global(i32 %x, i32 %y) + ret <3 x i32> %call +} + +define <4 x i32> @__clc_vload4_uint__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <4 x i32> @__clc_vload4_impl_i32__global(i32 %x, i32 %y) + ret <4 x i32> %call +} + +define <8 x i32> @__clc_vload8_uint__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <8 x i32> @__clc_vload8_impl_i32__global(i32 %x, i32 %y) + ret <8 x i32> %call +} + +define <16 x i32> @__clc_vload16_uint__global(i32 %x, i32 %y) nounwind readonly alwaysinline { + %call = call <16 x i32> @__clc_vload16_impl_i32__global(i32 %x, i32 %y) + ret <16 x i32> %call +} diff --git a/generic/lib/shared/vload_impl.ll b/generic/lib/shared/vload_impl.ll new file mode 100644 index 0000000..ae719e0 --- /dev/null +++ b/generic/lib/shared/vload_impl.ll @@ -0,0 +1,49 @@ +; This provides optimized implementations of vload4/8/16 for 32-bit int/uint + +define <2 x i32> @__clc_vload2_impl_i32__global(i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind readonly alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <2 x i32> addrspace(1)* + %4 = load <2 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret <2 x i32> %4 +} + +define <3 x i32> @__clc_vload3_impl_i32__global(i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind readonly alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <3 x i32> addrspace(1)* + %4 = load <3 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret <3 x i32> %4 +} + +define <4 x i32> @__clc_vload4_impl_i32__global(i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind readonly alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <4 x i32> addrspace(1)* + %4 = load <4 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret <4 x i32> %4 +} + +define <8 x i32> @__clc_vload8_impl_i32__global(i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind readonly alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <8 x i32> addrspace(1)* + %4 = load <8 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret <8 x i32> %4 +} + +define <16 x i32> @__clc_vload16_impl_i32__global(i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind readonly alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <16 x i32> addrspace(1)* + %4 = load <16 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret <16 x i32> %4 +} + +!1 = metadata !{metadata !"char", metadata !5} +!2 = metadata !{metadata !"short", metadata !5} +!3 = metadata !{metadata !"int", metadata !5} +!4 = metadata !{metadata !"long", metadata !5} +!5 = metadata !{metadata !"omnipotent char", metadata !6} +!6 = metadata !{metadata !"Simple C/C++ TBAA"} + diff --git a/generic/lib/shared/vstore.cl b/generic/lib/shared/vstore.cl index 522b1d6..c6d9551 100644 --- a/generic/lib/shared/vstore.cl +++ b/generic/lib/shared/vstore.cl @@ -34,13 +34,12 @@ VSTORE_VECTORIZE(SCALAR_GENTYPE, __local) \ VSTORE_VECTORIZE(SCALAR_GENTYPE, __global) \ +//int/uint are special... see below #define VSTORE_TYPES() \ VSTORE_ADDR_SPACES(char) \ VSTORE_ADDR_SPACES(uchar) \ VSTORE_ADDR_SPACES(short) \ VSTORE_ADDR_SPACES(ushort) \ - VSTORE_ADDR_SPACES(int) \ - VSTORE_ADDR_SPACES(uint) \ VSTORE_ADDR_SPACES(long) \ VSTORE_ADDR_SPACES(ulong) \ VSTORE_ADDR_SPACES(float) \ @@ -52,3 +51,58 @@ VSTORE_TYPES() VSTORE_ADDR_SPACES(double) #endif +VSTORE_VECTORIZE(int, __private) +VSTORE_VECTORIZE(int, __local) +VSTORE_VECTORIZE(uint, __private) +VSTORE_VECTORIZE(uint, __local) + +_CLC_OVERLOAD _CLC_DEF void vstore2(int2 vec, size_t offset, global int *mem) { + mem[offset] = vec.s0; + mem[offset+1] = vec.s1; +} +_CLC_OVERLOAD _CLC_DEF void vstore3(int3 vec, size_t offset, global int *mem) { + mem[offset] = vec.s0; + mem[offset+1] = vec.s1; + mem[offset+2] = vec.s2; +} +_CLC_OVERLOAD _CLC_DEF void vstore2(uint2 vec, size_t offset, global uint *mem) { + mem[offset] = vec.s0; + mem[offset+1] = vec.s1; +} +_CLC_OVERLOAD _CLC_DEF void vstore3(uint3 vec, size_t offset, global uint *mem) { + mem[offset] = vec.s0; + mem[offset+1] = vec.s1; + mem[offset+2] = vec.s2; +} + +/*Note: R600 probably doesn't support store <2 x ?> and <3 x ?>... so + * they aren't actually overridden here... lowest-common-denominator + */ +_CLC_DECL void __clc_vstore4_int__global(int4 vec, size_t offset, __global int *); +_CLC_DECL void __clc_vstore8_int__global(int8 vec, size_t offset, __global int *); +_CLC_DECL void __clc_vstore16_int__global(int16 vec, size_t offset, __global int *); + +_CLC_OVERLOAD _CLC_DEF void vstore4(int4 vec, size_t offset, global int *x) { + __clc_vstore4_int__global(vec, offset, x); +} +_CLC_OVERLOAD _CLC_DEF void vstore8(int8 vec, size_t offset, global int *x) { + __clc_vstore8_int__global(vec, offset, x); +} +_CLC_OVERLOAD _CLC_DEF void vstore16(int16 vec, size_t offset, global int *x) { + __clc_vstore16_int__global(vec, offset, x); +} + +_CLC_DECL void __clc_vstore4_uint__global(uint4 vec, size_t offset, __global uint *); +_CLC_DECL void __clc_vstore8_uint__global(uint8 vec, size_t offset, __global uint *); +_CLC_DECL void __clc_vstore16_uint__global(uint16 vec, size_t offset, __global uint *); + +_CLC_OVERLOAD _CLC_DEF void vstore4(uint4 vec, size_t offset, global uint *x) { + __clc_vstore4_uint__global(vec, offset, x); +} +_CLC_OVERLOAD _CLC_DEF void vstore8(uint8 vec, size_t offset, global uint *x) { + __clc_vstore8_uint__global(vec, offset, x); +} +_CLC_OVERLOAD _CLC_DEF void vstore16(uint16 vec, size_t offset, global uint *x) { + __clc_vstore16_uint__global(vec, offset, x); +} + diff --git a/generic/lib/shared/vstore_if.ll b/generic/lib/shared/vstore_if.ll new file mode 100644 index 0000000..30eb552 --- /dev/null +++ b/generic/lib/shared/vstore_if.ll @@ -0,0 +1,59 @@ +;Start int global vstore + +declare void @__clc_vstore2_impl_i32__global(<2 x i32> %vec, i32 %x, i32 %y) +declare void @__clc_vstore3_impl_i32__global(<3 x i32> %vec, i32 %x, i32 %y) +declare void @__clc_vstore4_impl_i32__global(<4 x i32> %vec, i32 %x, i32 %y) +declare void @__clc_vstore8_impl_i32__global(<8 x i32> %vec, i32 %x, i32 %y) +declare void @__clc_vstore16_impl_i32__global(<16 x i32> %vec, i32 %x, i32 %y) + +define void @__clc_vstore2_int__global(<2 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore2_impl_i32__global(<2 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore3_int__global(<3 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore3_impl_i32__global(<3 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore4_int__global(<4 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore4_impl_i32__global(<4 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore8_int__global(<8 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore8_impl_i32__global(<8 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore16_int__global(<16 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore16_impl_i32__global(<16 x i32> %vec, i32 %x, i32 %y) + ret void +} + + +;Start uint global vstore +define void @__clc_vstore2_uint__global(<2 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore2_impl_i32__global(<2 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore3_uint__global(<3 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore3_impl_i32__global(<3 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore4_uint__global(<4 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore4_impl_i32__global(<4 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore8_uint__global(<8 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore8_impl_i32__global(<8 x i32> %vec, i32 %x, i32 %y) + ret void +} + +define void @__clc_vstore16_uint__global(<16 x i32> %vec, i32 %x, i32 %y) nounwind alwaysinline { + call void @__clc_vstore16_impl_i32__global(<16 x i32> %vec, i32 %x, i32 %y) + ret void +}
\ No newline at end of file diff --git a/generic/lib/shared/vstore_impl.ll b/generic/lib/shared/vstore_impl.ll new file mode 100644 index 0000000..3baab5e --- /dev/null +++ b/generic/lib/shared/vstore_impl.ll @@ -0,0 +1,50 @@ +; This provides optimized implementations of vstore4/8/16 for 32-bit int/uint + +define void @__clc_vstore2_impl_i32__global(<2 x i32> %vec, i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <2 x i32> addrspace(1)* + store <2 x i32> %vec, <2 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret void +} + +define void @__clc_vstore3_impl_i32__global(<3 x i32> %vec, i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <3 x i32> addrspace(1)* + store <3 x i32> %vec, <3 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret void +} + +define void @__clc_vstore4_impl_i32__global(<4 x i32> %vec, i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <4 x i32> addrspace(1)* + store <4 x i32> %vec, <4 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret void +} + +define void @__clc_vstore8_impl_i32__global(<8 x i32> %vec, i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <8 x i32> addrspace(1)* + store <8 x i32> %vec, <8 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret void +} + +define void @__clc_vstore16_impl_i32__global(<16 x i32> %vec, i32 %offset, i32 addrspace(1)* nocapture %addr) nounwind alwaysinline { + %1 = ptrtoint i32 addrspace(1)* %addr to i32 + %2 = add i32 %1, %offset + %3 = inttoptr i32 %2 to <16 x i32> addrspace(1)* + store <16 x i32> %vec, <16 x i32> addrspace(1)* %3, align 4, !tbaa !3 + ret void +} + + +!1 = metadata !{metadata !"char", metadata !5} +!2 = metadata !{metadata !"short", metadata !5} +!3 = metadata !{metadata !"int", metadata !5} +!4 = metadata !{metadata !"long", metadata !5} +!5 = metadata !{metadata !"omnipotent char", metadata !6} +!6 = metadata !{metadata !"Simple C/C++ TBAA"} + |