From 4cb7cf276df36a15e9b416f3d0b55d5604615112 Mon Sep 17 00:00:00 2001
From: Aaron Watry <awatry@gmail.com>
Date: Tue, 16 Jul 2013 14:28:58 +0000
Subject: [PATCH] libclc: vload/vstore disable assembly and fix offset
 calculation

This commit gets us back to pure CLC and fixes offset calculations.

The next commit will re-enable the assembly implementation for R600,
fix bugs related to 64-bit address spaces, and also fix the
incorrect assumption that address space identifiers are the same in
all architectures.

llvm-svn: 186415
---
 libclc/generic/lib/SOURCES             |  2 -
 libclc/generic/lib/shared/vload.cl     | 64 +++------------------------
 libclc/generic/lib/shared/vload_if.ll  | 60 -------------------------
 libclc/generic/lib/shared/vstore.cl    | 80 ++++++----------------------------
 libclc/generic/lib/shared/vstore_if.ll | 59 -------------------------
 5 files changed, 20 insertions(+), 245 deletions(-)
 delete mode 100644 libclc/generic/lib/shared/vload_if.ll
 delete mode 100644 libclc/generic/lib/shared/vstore_if.ll

diff --git a/libclc/generic/lib/SOURCES b/libclc/generic/lib/SOURCES
index c2da3d7..21a7eaa 100644
--- a/libclc/generic/lib/SOURCES
+++ b/libclc/generic/lib/SOURCES
@@ -26,10 +26,8 @@ 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/libclc/generic/lib/shared/vload.cl b/libclc/generic/lib/shared/vload.cl
index 4dd7918..6793072 100644
--- a/libclc/generic/lib/shared/vload.cl
+++ b/libclc/generic/lib/shared/vload.cl
@@ -2,23 +2,23 @@
 
 #define VLOAD_VECTORIZE(PRIM_TYPE, ADDR_SPACE) \
   _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##2 vload2(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
-    return (PRIM_TYPE##2)(x[offset] , x[offset+1]); \
+    return (PRIM_TYPE##2)(x[2*offset] , x[2*offset+1]); \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##3 vload3(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
-    return (PRIM_TYPE##3)(x[offset] , x[offset+1], x[offset+2]); \
+    return (PRIM_TYPE##3)(x[3*offset] , x[3*offset+1], x[3*offset+2]); \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##4 vload4(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
-    return (PRIM_TYPE##4)(x[offset], x[offset+1], x[offset+2], x[offset+3]); \
+    return (PRIM_TYPE##4)(x[4*offset], x[4*offset+1], x[4*offset+2], x[4*offset+3]); \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##8 vload8(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
-    return (PRIM_TYPE##8)(vload4(offset, x), vload4(offset+4, x)); \
+    return (PRIM_TYPE##8)(vload4(0, &x[8*offset]), vload4(1, &x[8*offset])); \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF PRIM_TYPE##16 vload16(size_t offset, const ADDR_SPACE PRIM_TYPE *x) { \
-    return (PRIM_TYPE##16)(vload8(offset, x), vload8(offset+8, x)); \
+    return (PRIM_TYPE##16)(vload8(0, &x[16*offset]), vload8(1, &x[16*offset])); \
   } \
 
 #define VLOAD_ADDR_SPACES(__CLC_SCALAR_GENTYPE) \
@@ -27,12 +27,13 @@
     VLOAD_VECTORIZE(__CLC_SCALAR_GENTYPE, __constant) \
     VLOAD_VECTORIZE(__CLC_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) \
@@ -43,54 +44,3 @@ VLOAD_TYPES()
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
     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/libclc/generic/lib/shared/vload_if.ll b/libclc/generic/lib/shared/vload_if.ll
deleted file mode 100644
index 2634d37..0000000
--- a/libclc/generic/lib/shared/vload_if.ll
+++ /dev/null
@@ -1,60 +0,0 @@
-;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/libclc/generic/lib/shared/vstore.cl b/libclc/generic/lib/shared/vstore.cl
index 17c2c4c..f6d360e 100644
--- a/libclc/generic/lib/shared/vstore.cl
+++ b/libclc/generic/lib/shared/vstore.cl
@@ -4,29 +4,29 @@
 
 #define VSTORE_VECTORIZE(PRIM_TYPE, ADDR_SPACE) \
   _CLC_OVERLOAD _CLC_DEF void vstore2(PRIM_TYPE##2 vec, size_t offset, ADDR_SPACE PRIM_TYPE *mem) { \
-    mem[offset] = vec.s0; \
-    mem[offset+1] = vec.s1; \
+    mem[2*offset] = vec.s0; \
+    mem[2*offset+1] = vec.s1; \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF void vstore3(PRIM_TYPE##3 vec, size_t offset, ADDR_SPACE PRIM_TYPE *mem) { \
-    mem[offset] = vec.s0; \
-    mem[offset+1] = vec.s1; \
-    mem[offset+2] = vec.s2; \
+    mem[3*offset] = vec.s0; \
+    mem[3*offset+1] = vec.s1; \
+    mem[3*offset+2] = vec.s2; \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF void vstore4(PRIM_TYPE##4 vec, size_t offset, ADDR_SPACE PRIM_TYPE *mem) { \
-    vstore2(vec.lo, offset, mem); \
-    vstore2(vec.hi, offset+2, mem); \
+    vstore2(vec.lo, 0, &mem[offset*4]); \
+    vstore2(vec.hi, 1, &mem[offset*4]); \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF void vstore8(PRIM_TYPE##8 vec, size_t offset, ADDR_SPACE PRIM_TYPE *mem) { \
-    vstore4(vec.lo, offset, mem); \
-    vstore4(vec.hi, offset+4, mem); \
+    vstore4(vec.lo, 0, &mem[offset*8]); \
+    vstore4(vec.hi, 1, &mem[offset*8]); \
   } \
 \
   _CLC_OVERLOAD _CLC_DEF void vstore16(PRIM_TYPE##16 vec, size_t offset, ADDR_SPACE PRIM_TYPE *mem) { \
-    vstore8(vec.lo, offset, mem); \
-    vstore8(vec.hi, offset+8, mem); \
+    vstore8(vec.lo, 0, &mem[offset*16]); \
+    vstore8(vec.hi, 1, &mem[offset*16]); \
   } \
 
 #define VSTORE_ADDR_SPACES(__CLC_SCALAR___CLC_GENTYPE) \
@@ -34,12 +34,13 @@
     VSTORE_VECTORIZE(__CLC_SCALAR___CLC_GENTYPE, __local) \
     VSTORE_VECTORIZE(__CLC_SCALAR___CLC_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) \
@@ -50,58 +51,3 @@ VSTORE_TYPES()
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
     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/libclc/generic/lib/shared/vstore_if.ll b/libclc/generic/lib/shared/vstore_if.ll
deleted file mode 100644
index 30eb552..0000000
--- a/libclc/generic/lib/shared/vstore_if.ll
+++ /dev/null
@@ -1,59 +0,0 @@
-;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
-- 
2.7.4