r600c: add big endian support for r6xx/r7xx

Signed-off-by: Cedric Cano <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

11 files changed, 508 insertions, 50 deletions

diff --git a/src/mesa/drivers/dri/r600/defaultendian.h b/src/mesa/drivers/dri/r600/defaultendian.h
index 32caf32cd2e..75bd61c3cd4 100644
--- a/src/mesa/drivers/dri/r600/defaultendian.h
+++ b/src/mesa/drivers/dri/r600/defaultendian.h
@@ -29,8 +29,8 @@
 #define _DEFINEENDIAN_H_
 
 //We have to choose a reg bits orientation if there is no compile flag for it.
-#if defined(LITTLEENDIAN_CPU)
-#elif defined(BIGENDIAN_CPU)
+#ifdef MESA_BIG_ENDIAN
+#define BIGENDIAN_CPU
 #else
 #define LITTLEENDIAN_CPU
 #endif
diff --git a/src/mesa/drivers/dri/r600/r600_blit.c b/src/mesa/drivers/dri/r600/r600_blit.c
index 31c32d62f9a..2d47afdcbbf 100644
--- a/src/mesa/drivers/dri/r600/r600_blit.c
+++ b/src/mesa/drivers/dri/r600/r600_blit.c
@@ -94,17 +94,17 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 {
     uint32_t cb_color0_base, cb_color0_size = 0, cb_color0_info = 0, cb_color0_view = 0;
     int id = 0;
-    uint32_t comp_swap, format;
+    uint32_t endian, comp_swap, format;
     BATCH_LOCALS(&context->radeon);
 
     cb_color0_base = dst_offset / 256;
+	endian = ENDIAN_NONE;
 
     SETfield(cb_color0_size, (nPitchInPixel / 8) - 1,
              PITCH_TILE_MAX_shift, PITCH_TILE_MAX_mask);
     SETfield(cb_color0_size, ((nPitchInPixel * h) / 64) - 1,
              SLICE_TILE_MAX_shift, SLICE_TILE_MAX_mask);
 
-    SETfield(cb_color0_info, ENDIAN_NONE, ENDIAN_shift, ENDIAN_mask);
     SETfield(cb_color0_info, ARRAY_LINEAR_GENERAL,
              CB_COLOR0_INFO__ARRAY_MODE_shift, CB_COLOR0_INFO__ARRAY_MODE_mask);
 
@@ -112,24 +112,36 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 
     switch(mesa_format) {
     case MESA_FORMAT_RGBA8888:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_8_8_8;
             comp_swap = SWAP_STD_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_SIGNED_RGBA8888:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_8_8_8;
             comp_swap = SWAP_STD_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_SNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_RGBA8888_REV:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_8_8_8;
             comp_swap = SWAP_STD;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_SIGNED_RGBA8888_REV:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_8_8_8;
             comp_swap = SWAP_STD;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
@@ -137,6 +149,9 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
             break;
     case MESA_FORMAT_ARGB8888:
     case MESA_FORMAT_XRGB8888:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_8_8_8;
             comp_swap = SWAP_ALT;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
@@ -144,54 +159,81 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
             break;
     case MESA_FORMAT_ARGB8888_REV:
     case MESA_FORMAT_XRGB8888_REV:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_8_8_8;
             comp_swap = SWAP_ALT_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_RGB565:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
+		    comp_swap = SWAP_STD_REV;	
             format = COLOR_5_6_5;
-            comp_swap = SWAP_STD_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_RGB565_REV:
-            format = COLOR_5_6_5;
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             comp_swap = SWAP_STD;
+            format = COLOR_5_6_5;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_ARGB4444:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_4_4_4_4;
             comp_swap = SWAP_ALT;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_ARGB4444_REV:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_4_4_4_4;
             comp_swap = SWAP_ALT_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_ARGB1555:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_1_5_5_5;
             comp_swap = SWAP_ALT;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_ARGB1555_REV:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_1_5_5_5;
             comp_swap = SWAP_ALT_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_AL88:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_8_8;
             comp_swap = SWAP_STD;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_AL88_REV:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_8_8;
             comp_swap = SWAP_STD_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
@@ -223,6 +265,9 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_RGBA_FLOAT32:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_32_32_32_32_FLOAT;
             comp_swap = SWAP_STD;
 	    SETbit(cb_color0_info, BLEND_FLOAT32_bit);
@@ -230,12 +275,18 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_RGBA_FLOAT16:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_16_16_16_16_FLOAT;
             comp_swap = SWAP_STD;
 	    CLEARbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_ALPHA_FLOAT32:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_32_FLOAT;
             comp_swap = SWAP_ALT_REV;
 	    SETbit(cb_color0_info, BLEND_FLOAT32_bit);
@@ -243,12 +294,18 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_ALPHA_FLOAT16:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_16_FLOAT;
             comp_swap = SWAP_ALT_REV;
 	    CLEARbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_LUMINANCE_FLOAT32:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_32_FLOAT;
             comp_swap = SWAP_ALT;
 	    SETbit(cb_color0_info, BLEND_FLOAT32_bit);
@@ -256,12 +313,18 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_LUMINANCE_FLOAT16:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_16_FLOAT;
             comp_swap = SWAP_ALT;
 	    CLEARbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_LUMINANCE_ALPHA_FLOAT32:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_32_32_FLOAT;
             comp_swap = SWAP_ALT_REV;
 	    SETbit(cb_color0_info, BLEND_FLOAT32_bit);
@@ -269,12 +332,18 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_LUMINANCE_ALPHA_FLOAT16:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_16_16_FLOAT;
             comp_swap = SWAP_ALT_REV;
 	    CLEARbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_INTENSITY_FLOAT32: /* X, X, X, X */
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_32_FLOAT;
             comp_swap = SWAP_STD;
 	    SETbit(cb_color0_info, BLEND_FLOAT32_bit);
@@ -282,6 +351,9 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_FLOAT, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_INTENSITY_FLOAT16: /* X, X, X, X */
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_16_FLOAT;
             comp_swap = SWAP_STD;
 	    CLEARbit(cb_color0_info, SOURCE_FORMAT_bit);
@@ -289,6 +361,9 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
             break;
     case MESA_FORMAT_X8_Z24:
     case MESA_FORMAT_S8_Z24:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_24;
             comp_swap = SWAP_STD;
 	    SETfield(cb_color0_info, ARRAY_1D_TILED_THIN1,
@@ -297,6 +372,9 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_Z24_S8:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_24_8;
             comp_swap = SWAP_STD;
 	    SETfield(cb_color0_info, ARRAY_1D_TILED_THIN1,
@@ -305,6 +383,9 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_Z16:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_16;
             comp_swap = SWAP_STD;
 	    SETfield(cb_color0_info, ARRAY_1D_TILED_THIN1,
@@ -313,6 +394,9 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_Z32:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_32;
             comp_swap = SWAP_STD;
 	    SETfield(cb_color0_info, ARRAY_1D_TILED_THIN1,
@@ -321,12 +405,18 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
 	    SETfield(cb_color0_info, NUMBER_UNORM, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_SARGB8:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN32;
+#endif
             format = COLOR_8_8_8_8;
             comp_swap = SWAP_ALT;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
 	    SETfield(cb_color0_info, NUMBER_SRGB, NUMBER_TYPE_shift, NUMBER_TYPE_mask);
             break;
     case MESA_FORMAT_SLA8:
+#ifdef MESA_BIG_ENDIAN
+			endian = ENDIAN_8IN16;
+#endif
             format = COLOR_8_8;
             comp_swap = SWAP_ALT_REV;
 	    SETbit(cb_color0_info, SOURCE_FORMAT_bit);
@@ -348,6 +438,7 @@ set_render_target(context_t *context, struct radeon_bo *bo, gl_format mesa_forma
     if (context->radeon.radeonScreen->chip_family >= CHIP_FAMILY_RV770)
 	    CLEARbit(cb_color0_info, BLEND_FLOAT32_bit);
 
+    SETfield(cb_color0_info, endian, ENDIAN_shift, ENDIAN_mask);
     SETfield(cb_color0_info, format, CB_COLOR0_INFO__FORMAT_shift,
              CB_COLOR0_INFO__FORMAT_mask);
     SETfield(cb_color0_info, comp_swap, COMP_SWAP_shift, COMP_SWAP_mask);
@@ -426,10 +517,10 @@ static inline void load_shaders(struct gl_context * ctx)
     shader = context->blit_bo->ptr;
 
     for(i=0; i<sizeof(r6xx_vs)/4; i++) {
-        shader[128+i] = r6xx_vs[i];
+        shader[128+i] = CPU_TO_LE32(r6xx_vs[i]);
     }
     for(i=0; i<sizeof(r6xx_ps)/4; i++) {
-        shader[256+i] = r6xx_ps[i];
+        shader[256+i] = CPU_TO_LE32(r6xx_ps[i]);
     }
 
     radeon_bo_unmap(context->blit_bo);
@@ -521,6 +612,8 @@ static inline void
 set_vtx_resource(context_t *context)
 {
     struct radeon_bo *bo = context->blit_bo;
+	uint32_t sq_vtx_constant_word2 = 0;
+
     BATCH_LOCALS(&context->radeon);
 
     BEGIN_BATCH_NO_AUTOSTATE(6);
@@ -543,13 +636,19 @@ set_vtx_resource(context_t *context)
     else
 	    r700SyncSurf(context, bo, RADEON_GEM_DOMAIN_GTT, 0, VC_ACTION_ENA_bit);
 
+	sq_vtx_constant_word2 = 0
+#ifdef MESA_BIG_ENDIAN
+		| (SQ_ENDIAN_8IN32 << SQ_VTX_CONSTANT_WORD2_0__ENDIAN_SWAP_shift)
+#endif
+		| (16 << SQ_VTX_CONSTANT_WORD2_0__STRIDE_shift);
+
     BEGIN_BATCH_NO_AUTOSTATE(9 + 2);
 
     R600_OUT_BATCH(CP_PACKET3(R600_IT_SET_RESOURCE, 7));
     R600_OUT_BATCH(SQ_FETCH_RESOURCE_VS_OFFSET * FETCH_RESOURCE_STRIDE);
     R600_OUT_BATCH(0);
     R600_OUT_BATCH(48 - 1);
-    R600_OUT_BATCH(16 << SQ_VTX_CONSTANT_WORD2_0__STRIDE_shift);
+    R600_OUT_BATCH(sq_vtx_constant_word2);
     R600_OUT_BATCH(1 << MEM_REQUEST_SIZE_shift);
     R600_OUT_BATCH(0);
     R600_OUT_BATCH(0);
@@ -670,11 +769,11 @@ set_tex_resource(context_t * context,
 	    SETfield(sq_tex_resource1, FMT_8_8_8_8,
 		     SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
-	    SETfield(sq_tex_resource4, SQ_SEL_1,
+	    SETfield(sq_tex_resource4, SQ_SEL_Y,
 		     SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 	    SETfield(sq_tex_resource4, SQ_SEL_Z,
 		     SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
-	    SETfield(sq_tex_resource4, SQ_SEL_W,
+	    SETfield(sq_tex_resource4, SQ_SEL_1,
 		     SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 	    SETfield(sq_tex_resource4, SQ_SEL_X,
 		     SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
diff --git a/src/mesa/drivers/dri/r600/r600_blit_shaders.h b/src/mesa/drivers/dri/r600/r600_blit_shaders.h
index 492dde96368..2124f7673d7 100644
--- a/src/mesa/drivers/dri/r600/r600_blit_shaders.h
+++ b/src/mesa/drivers/dri/r600/r600_blit_shaders.h
@@ -10,7 +10,11 @@ const uint32_t r6xx_vs[] =
         0x00000000,
         0x3c000000, // SQ_VTX_INST_FETCH BUFFER_ID(0) MEGA_FETCH_COUNT(16)
         0x68cd1000, // DST_GPR(0) DST_SWZ: XYZW DATA_FORMAT(35) SQ_NUM_FORMAT_SCALED SQ_FORMAT_COMP_SIGNED
+#ifdef MESA_BIG_ENDIAN
+		0x000a0000, // ENDIAN_SWAP(SQ_ENDIAN_8IN32) MEGA_FETCH(1)
+#else
         0x00080000, // ENDIAN_SWAP(SQ_ENDIAN_NONE) MEGA_FETCH(1)
+#endif
         0x00000000, // VTX_DWORD_PAD
 };
 
diff --git a/src/mesa/drivers/dri/r600/r600_emit.c b/src/mesa/drivers/dri/r600/r600_emit.c
index 53ece9a3505..c6916ed98a3 100644
--- a/src/mesa/drivers/dri/r600/r600_emit.c
+++ b/src/mesa/drivers/dri/r600/r600_emit.c
@@ -100,14 +100,17 @@ GLboolean r600EmitShaderConsts(struct gl_context * ctx,
                                int sizeinBYTE)
 {	
 	struct radeon_bo * pbo = (struct radeon_bo *)constbo;
-	uint8_t *out;
+	uint32_t *out;
+	int i;
 
 	radeon_bo_map(pbo, 1);
 
-	out = (uint8_t*)(pbo->ptr);
-    out = (uint8_t*)ADD_POINTERS(pbo->ptr, bo_offset);
+	out = (uint32_t*)(pbo->ptr);
+    out = (uint32_t*)ADD_POINTERS(pbo->ptr, bo_offset);
 
-	memcpy(out, data, sizeinBYTE);
+	for(i = 0; i < sizeinBYTE / 4; i++) {
+		out[i] = CPU_TO_LE32(*((uint32_t *)data + i));
+	}
 
 	radeon_bo_unmap(pbo);
 
@@ -123,6 +126,7 @@ GLboolean r600EmitShader(struct gl_context * ctx,
 	radeonContextPtr radeonctx = RADEON_CONTEXT(ctx);
 	struct radeon_bo * pbo;
 	uint32_t *out;
+	int i;
 shader_again_alloc:
 	pbo = radeon_bo_open(radeonctx->radeonScreen->bom,
 			0,
@@ -154,7 +158,9 @@ shader_again_alloc:
 
 	out = (uint32_t*)(pbo->ptr);
 
-	memcpy(out, data, sizeinDWORD * 4);
+	for(i = 0; i < sizeinDWORD; i++) {
+		out[i] = CPU_TO_LE32(*((uint32_t *)data + i));
+	}
 
 	radeon_bo_unmap(pbo);
 
diff --git a/src/mesa/drivers/dri/r600/r600_texstate.c b/src/mesa/drivers/dri/r600/r600_texstate.c
index 3568a5515be..949db29c189 100644
--- a/src/mesa/drivers/dri/r600/r600_texstate.c
+++ b/src/mesa/drivers/dri/r600/r600_texstate.c
@@ -109,6 +109,16 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_8_8_8_8,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
@@ -117,6 +127,7 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		if (mesa_format == MESA_FORMAT_SIGNED_RGBA8888) {
 			SETfield(t->SQ_TEX_RESOURCE4, SQ_FORMAT_COMP_SIGNED,
 				 FORMAT_COMP_X_shift, FORMAT_COMP_X_mask);
@@ -133,6 +144,16 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_8_8_8_8,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -141,6 +162,7 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		if (mesa_format == MESA_FORMAT_SIGNED_RGBA8888_REV) {
 			SETfield(t->SQ_TEX_RESOURCE4, SQ_FORMAT_COMP_SIGNED,
 				 FORMAT_COMP_X_shift, FORMAT_COMP_X_mask);
@@ -156,6 +178,16 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_8_8_8_8,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -164,11 +196,22 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_XRGB8888:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_8_8_8_8,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -177,24 +220,46 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_XRGB8888_REV:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_8_8_8_8,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
-		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_ARGB8888_REV:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_8_8_8_8,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
@@ -203,11 +268,22 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_RGB888:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_8_8_8,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -216,11 +292,22 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_RGB565:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_5_6_5,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -229,11 +316,23 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
+
 		break;
 	case MESA_FORMAT_RGB565_REV:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_5_6_5,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+        SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -242,11 +341,22 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_1,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_ARGB4444:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_4_4_4_4,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
 
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -255,11 +365,21 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_ARGB4444_REV:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_4_4_4_4,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
-
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
@@ -268,11 +388,21 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_ARGB1555:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_1_5_5_5,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
-
+#ifdef MESA_BIG_ENDIAN
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
@@ -281,11 +411,21 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_ARGB1555_REV:
 		SETfield(t->SQ_TEX_RESOURCE1, FMT_1_5_5_5,
 			 SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_shift, SQ_TEX_RESOURCE_WORD1_0__DATA_FORMAT_mask);
-
+#ifdef MESA_BIG_ENDIAN
+       SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Y_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
+		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_W,
+			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#else
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Y,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_X_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_Z,
@@ -294,6 +434,7 @@ static GLboolean r600GetTexFormat(struct gl_texture_object *tObj, gl_format mesa
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_Z_mask);
 		SETfield(t->SQ_TEX_RESOURCE4, SQ_SEL_X,
 			 SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_shift, SQ_TEX_RESOURCE_WORD4_0__DST_SEL_W_mask);
+#endif
 		break;
 	case MESA_FORMAT_AL88:
 	case MESA_FORMAT_AL88_REV: /* TODO : Check this. */
diff --git a/src/mesa/drivers/dri/r600/r700_assembler.c b/src/mesa/drivers/dri/r600/r700_assembler.c
index 4ed37033902..216ff0b941c 100644
--- a/src/mesa/drivers/dri/r600/r700_assembler.c
+++ b/src/mesa/drivers/dri/r600/r700_assembler.c
@@ -1188,7 +1188,12 @@ GLboolean EG_assemble_vfetch_instruction(r700_AssemblerBase* pAsm,
     SETfield(vfetch_instruction_ptr->m_Word2.val, 0,
              EG_VTX_WORD2__OFFSET_shift,
              EG_VTX_WORD2__OFFSET_mask); 
-    SETfield(vfetch_instruction_ptr->m_Word2.val, SQ_ENDIAN_NONE,
+    SETfield(vfetch_instruction_ptr->m_Word2.val, 
+#ifdef MESA_BIG_ENDIAN
+			 SQ_ENDIAN_8IN32,
+#else
+			 SQ_ENDIAN_NONE,
+#endif
              EG_VTX_WORD2__ENDIAN_SWAP_shift,
              EG_VTX_WORD2__ENDIAN_SWAP_mask);
     SETfield(vfetch_instruction_ptr->m_Word2.val, 0,
@@ -1294,7 +1299,11 @@ GLboolean assemble_vfetch_instruction2(r700_AssemblerBase* pAsm,
 
 	vfetch_instruction_ptr->m_Word1.f.use_const_fields = 1;
     vfetch_instruction_ptr->m_Word1.f.data_format      = data_format;
+#ifdef MESA_BIG_ENDIAN
+    vfetch_instruction_ptr->m_Word2.f.endian_swap      = SQ_ENDIAN_8IN32;
+#else
     vfetch_instruction_ptr->m_Word2.f.endian_swap      = SQ_ENDIAN_NONE;
+#endif
 
     if(1 == _signed)
     {
diff --git a/src/mesa/drivers/dri/r600/r700_assembler.h b/src/mesa/drivers/dri/r600/r700_assembler.h
index c7c7ab2d4ff..8a9ccd1c4ec 100644
--- a/src/mesa/drivers/dri/r600/r700_assembler.h
+++ b/src/mesa/drivers/dri/r600/r700_assembler.h
@@ -130,6 +130,27 @@ typedef unsigned int BITS;
 
 typedef struct PVSDSTtag 
 {
+#ifdef MESA_BIG_ENDIAN
+	BITS addrmode1:1; //32
+	BITS addrmode0:1; //31   //29
+
+	BITS dualop:1;    // 30  //26
+
+	BITS op3:1;       // 29  Represents *_OP3_* ALU opcode
+
+	BITS writew:1;     //28
+	BITS writez:1;
+	BITS writey:1;
+	BITS writex:1;
+
+	BITS reg:10;       //24   //20
+	BITS rtype:3;
+
+	BITS pred_inv  :1; //11   //8
+	BITS predicated:1; //10   //8
+	BITS math:1;
+	BITS opcode:8;     //(:6)  //@@@ really should be 10 bits for OP2
+#else
 	BITS opcode:8;     //(:6)  //@@@ really should be 10 bits for OP2
 	BITS math:1;
 	BITS predicated:1; //10   //8
@@ -149,17 +170,41 @@ typedef struct PVSDSTtag
 
 	BITS addrmode0:1; //31   //29
 	BITS addrmode1:1; //32
+#endif
 } PVSDST;
 
 typedef struct PVSINSTtag
 {
+#ifdef MESA_BIG_ENDIAN
+    BITS index_mode   :3;
+    BITS SaturateMode :2; 
+    BITS literal_slots      :2; 
+#else
     BITS literal_slots      :2; 
     BITS SaturateMode :2; 
     BITS index_mode   :3;
+#endif
 } PVSINST;
 
 typedef struct PVSSRCtag 
 {
+#ifdef MESA_BIG_ENDIAN
+	BITS addrmode1:1; //32
+	//BITS addrsel:2;
+	BITS negw:1;      //31
+	BITS negz:1;
+	BITS negy:1;
+	BITS negx:1;
+	BITS abs:1;
+
+	BITS swizzlew:3;  //26        
+	BITS swizzlez:3;
+	BITS swizzley:3;
+	BITS swizzlex:3;
+	BITS reg:10;      //14     (8)
+	BITS addrmode0:1;        
+	BITS rtype:3;            
+#else
 	BITS rtype:3;            
 	BITS addrmode0:1;        
 	BITS reg:10;      //14     (8)
@@ -175,10 +220,24 @@ typedef struct PVSSRCtag
 	BITS negw:1;      //31
 	//BITS addrsel:2;
 	BITS addrmode1:1; //32
+#endif
 } PVSSRC;
 
 typedef struct PVSMATHtag 
 {
+#ifdef MESA_BIG_ENDIAN
+	BITS spare2:3;
+	BITS dstcomp:2; // select dest component
+	BITS negy:1;
+	BITS negx:1;
+	BITS opcode:4;
+	BITS dstoff:2; // 2 bits of dest offset into alt ram
+	BITS swizzley:3;
+	BITS swizzlex:3;
+	BITS reg:8;
+	BITS spare:1;
+	BITS rtype:4;
+#else
 	BITS rtype:4;
 	BITS spare:1;
 	BITS reg:8;
@@ -190,6 +249,7 @@ typedef struct PVSMATHtag
 	BITS negy:1;
 	BITS dstcomp:2; // select dest component
 	BITS spare2:3;
+#endif
 } PVSMATH;
 
 typedef union PVSDWORDtag 
@@ -204,6 +264,34 @@ typedef union PVSDWORDtag
 
 typedef struct VAP_OUT_VTX_FMT_0tag 
 {
+#ifdef MESA_BIG_ENDIAN
+	BITS resvd1:12;        // 20
+
+	BITS viewport_index:1; // 19   
+	BITS kill_flag:1;
+	BITS rta_index:1;      //     shares same channel as kill_flag
+	BITS edge_flag:1;      
+	BITS point_size:1;     // 15   
+
+	BITS depth:1;          // 14
+
+	BITS normal:1;    
+
+	BITS color7:1;
+	BITS color6:1;
+	BITS color5:1;
+	BITS color4:1;
+	BITS color3:1;
+	BITS color2:1;
+	BITS color1:1;
+	BITS color0:1;
+
+	BITS pos_param:1; // 4
+	BITS clip_dist1:1;
+	BITS clip_dist0:1;
+	BITS misc:1;
+	BITS pos:1;      // 0
+#else
 	BITS pos:1;      // 0
 	BITS misc:1;
 	BITS clip_dist0:1;
@@ -230,10 +318,23 @@ typedef struct VAP_OUT_VTX_FMT_0tag
 	BITS viewport_index:1; // 19   
 
 	BITS resvd1:12;        // 20
+#endif
 } VAP_OUT_VTX_FMT_0;
 
 typedef struct VAP_OUT_VTX_FMT_1tag 
 {
+#ifdef MESA_BIG_ENDIAN
+	BITS resvd:8;
+
+	BITS tex7comp:3;
+	BITS tex6comp:3;
+	BITS tex5comp:3;
+	BITS tex4comp:3;
+	BITS tex3comp:3;
+	BITS tex2comp:3;
+	BITS tex1comp:3;
+	BITS tex0comp:3;
+#else
 	BITS tex0comp:3;
 	BITS tex1comp:3;
 	BITS tex2comp:3;
@@ -244,10 +345,23 @@ typedef struct VAP_OUT_VTX_FMT_1tag
 	BITS tex7comp:3;
 
 	BITS resvd:8;
+#endif
 } VAP_OUT_VTX_FMT_1;
 
 typedef struct VAP_OUT_VTX_FMT_2tag 
 {
+#ifdef MESA_BIG_ENDIAN
+	BITS resvd:8;
+
+	BITS tex15comp:3;
+	BITS tex14comp:3;
+	BITS tex13comp:3;
+	BITS tex12comp:3;
+	BITS tex11comp:3;
+	BITS tex10comp:3;
+	BITS tex9comp:3;
+	BITS tex8comp:3;
+#else
 	BITS tex8comp :3;
 	BITS tex9comp :3;
 	BITS tex10comp:3;
@@ -258,10 +372,28 @@ typedef struct VAP_OUT_VTX_FMT_2tag
 	BITS tex15comp:3;
 
 	BITS resvd:8;
+#endif
 } VAP_OUT_VTX_FMT_2;
 
 typedef struct OUT_FRAGMENT_FMT_0tag 
 {
+#ifdef MESA_BIG_ENDIAN
+	BITS resvd1:20;
+
+	BITS mask:1;
+	BITS coverage_to_mask:1;
+	BITS stencil_ref:1;
+	BITS depth:1;
+
+	BITS color7:1;
+	BITS color6:1;
+	BITS color5:1;
+	BITS color4:1;
+	BITS color3:1;
+	BITS color2:1;
+	BITS color1:1;
+	BITS color0:1;
+#else
 	BITS color0:1;
 	BITS color1:1;
 	BITS color2:1;
@@ -277,6 +409,7 @@ typedef struct OUT_FRAGMENT_FMT_0tag
 	BITS mask:1;
 
 	BITS resvd1:20;
+#endif
 } OUT_FRAGMENT_FMT_0;
 
 typedef enum  CF_CLAUSE_TYPE 
diff --git a/src/mesa/drivers/dri/r600/r700_chip.c b/src/mesa/drivers/dri/r600/r700_chip.c
index 7980c449e02..10fa3f9762b 100644
--- a/src/mesa/drivers/dri/r600/r700_chip.c
+++ b/src/mesa/drivers/dri/r600/r700_chip.c
@@ -202,7 +202,15 @@ static void r700SetupVTXConstants(struct gl_context  * ctx,
     SETfield(uSQ_VTX_CONSTANT_WORD2_0, GetSurfaceFormat(pStreamDesc->type, pStreamDesc->size, NULL),
 	     SQ_VTX_CONSTANT_WORD2_0__DATA_FORMAT_shift,
 	     SQ_VTX_CONSTANT_WORD2_0__DATA_FORMAT_mask); /* TODO : trace back api for initial data type, not only GL_FLOAT */
-    
+	SETfield(uSQ_VTX_CONSTANT_WORD2_0, 
+#ifdef MESA_BIG_ENDIAN 
+			 SQ_ENDIAN_8IN32,
+#else
+			 SQ_ENDIAN_NONE,
+#endif
+             SQ_VTX_CONSTANT_WORD2_0__ENDIAN_SWAP_shift,
+             SQ_VTX_CONSTANT_WORD2_0__ENDIAN_SWAP_mask);
+
     if(GL_TRUE == pStreamDesc->normalize)
     {
         SETfield(uSQ_VTX_CONSTANT_WORD2_0, SQ_NUM_FORMAT_NORM,
diff --git a/src/mesa/drivers/dri/r600/r700_render.c b/src/mesa/drivers/dri/r600/r700_render.c
index bb09980ed88..2bd3b62bfdb 100644
--- a/src/mesa/drivers/dri/r600/r700_render.c
+++ b/src/mesa/drivers/dri/r600/r700_render.c
@@ -276,6 +276,16 @@ static void r700RunRenderPrimitive(struct gl_context * ctx, int start, int end,
             SETfield(vgt_index_type, DI_INDEX_SIZE_16_BIT, INDEX_TYPE_shift, INDEX_TYPE_mask);
     }
 
+	/* 16-bit indexes are packed in a 32-bit value */
+	SETfield(vgt_index_type,
+#if MESA_BIG_ENDIAN
+			VGT_DMA_SWAP_32_BIT,
+#else
+			VGT_DMA_SWAP_NONE,
+#endif
+			SWAP_MODE_shift, SWAP_MODE_mask);
+
+
     vgt_num_indices = num_indices;
     SETfield(vgt_draw_initiator, DI_SRC_SEL_DMA, SOURCE_SELECT_shift, SOURCE_SELECT_mask);
     SETfield(vgt_draw_initiator, DI_MAJOR_MODE_0, MAJOR_MODE_shift, MAJOR_MODE_mask);
@@ -348,6 +358,15 @@ static void r700RunRenderPrimitiveImmediate(struct gl_context * ctx, int start,
             SETfield(vgt_index_type, DI_INDEX_SIZE_16_BIT, INDEX_TYPE_shift, INDEX_TYPE_mask);
     }
 
+	/* 16-bit indexes are packed in a 32-bit value */
+	SETfield(vgt_index_type,
+#if MESA_BIG_ENDIAN
+			VGT_DMA_SWAP_32_BIT,
+#else
+			VGT_DMA_SWAP_NONE,
+#endif
+			SWAP_MODE_shift, SWAP_MODE_mask);
+
     vgt_num_indices = num_indices;
     SETfield(vgt_draw_initiator, DI_MAJOR_MODE_0, MAJOR_MODE_shift, MAJOR_MODE_mask);
 
diff --git a/src/mesa/drivers/dri/radeon/radeon_common.c b/src/mesa/drivers/dri/radeon/radeon_common.c
index 0d73c0e3b1b..bfc307ca987 100644
--- a/src/mesa/drivers/dri/radeon/radeon_common.c
+++ b/src/mesa/drivers/dri/radeon/radeon_common.c
@@ -966,7 +966,7 @@ static void radeon_print_state_atom(radeonContextPtr radeon, struct radeon_state
 
 	fprintf(stderr, "  emit %s %d/%d\n", state->name, dwords, state->cmd_size);
 
-	if (radeon_is_debug_enabled(RADEON_STATE, RADEON_TRACE)) {
+	if (state->cmd && radeon_is_debug_enabled(RADEON_STATE, RADEON_TRACE)) {
 		if (dwords > state->cmd_size)
 			dwords = state->cmd_size;
 		for (i = 0; i < dwords;) {
diff --git a/src/mesa/drivers/dri/radeon/radeon_span.c b/src/mesa/drivers/dri/radeon/radeon_span.c
index caf3f253d2a..8c6f2e49a5c 100644
--- a/src/mesa/drivers/dri/radeon/radeon_span.c
+++ b/src/mesa/drivers/dri/radeon/radeon_span.c
@@ -50,6 +50,17 @@ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 #define DBG 0
 
+#if defined(BYTE_ORDER) && defined(BIG_ENDIAN) && BYTE_ORDER == BIG_ENDIAN
+#if defined(__linux__)
+#include <byteswap.h>
+#define CPU_TO_LE16( x )	bswap_16( x )
+#define LE16_TO_CPU( x )	bswap_16( x )
+#endif /* __linux__ */
+#else
+#define CPU_TO_LE16( x )	( x )
+#define LE16_TO_CPU( x )	( x )
+#endif
+
 static void radeonSetSpanFunctions(struct radeon_renderbuffer *rrb);
 
 
@@ -579,7 +590,11 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_RGB565
 #define TAG2(x,y) radeon##x##_RGB565##y
 #if defined(RADEON_R600)
-#define GET_PTR(X,Y) r600_ptr_color(rrb, (X) + x_off, (Y) + y_off)
+#define GET_VALUE(_x, _y) (LE16_TO_CPU(*(GLushort*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
+#define PUT_VALUE(_x, _y, d) { \
+   GLushort *_ptr = (GLushort*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
+   *_ptr = CPU_TO_LE16(d);								\
+} while (0)
 #else
 #define GET_PTR(X,Y) radeon_ptr_2byte_8x2(rrb, (X) + x_off, (Y) + y_off)
 #endif
@@ -591,7 +606,11 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_RGB565_REV
 #define TAG2(x,y) radeon##x##_RGB565_REV##y
 #if defined(RADEON_R600)
-#define GET_PTR(X,Y) r600_ptr_color(rrb, (X) + x_off, (Y) + y_off)
+#define GET_VALUE(_x, _y) (LE16_TO_CPU(*(GLushort*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
+#define PUT_VALUE(_x, _y, d) { \
+   GLushort *_ptr = (GLushort*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
+   *_ptr = CPU_TO_LE16(d);								\
+} while (0)
 #else
 #define GET_PTR(X,Y) radeon_ptr_2byte_8x2(rrb, (X) + x_off, (Y) + y_off)
 #endif
@@ -605,7 +624,11 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_ARGB1555
 #define TAG2(x,y) radeon##x##_ARGB1555##y
 #if defined(RADEON_R600)
-#define GET_PTR(X,Y) r600_ptr_color(rrb, (X) + x_off, (Y) + y_off)
+#define GET_VALUE(_x, _y) (LE16_TO_CPU(*(GLushort*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
+#define PUT_VALUE(_x, _y, d) { \
+   GLushort *_ptr = (GLushort*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
+   *_ptr = CPU_TO_LE16(d);								\
+} while (0)
 #else
 #define GET_PTR(X,Y) radeon_ptr_2byte_8x2(rrb, (X) + x_off, (Y) + y_off)
 #endif
@@ -617,7 +640,11 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_ARGB1555_REV
 #define TAG2(x,y) radeon##x##_ARGB1555_REV##y
 #if defined(RADEON_R600)
-#define GET_PTR(X,Y) r600_ptr_color(rrb, (X) + x_off, (Y) + y_off)
+#define GET_VALUE(_x, _y) (LE16_TO_CPU(*(GLushort*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
+#define PUT_VALUE(_x, _y, d) { \
+   GLushort *_ptr = (GLushort*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
+   *_ptr = CPU_TO_LE16(d);								\
+} while (0)
 #else
 #define GET_PTR(X,Y) radeon_ptr_2byte_8x2(rrb, (X) + x_off, (Y) + y_off)
 #endif
@@ -631,7 +658,11 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_ARGB4444
 #define TAG2(x,y) radeon##x##_ARGB4444##y
 #if defined(RADEON_R600)
-#define GET_PTR(X,Y) r600_ptr_color(rrb, (X) + x_off, (Y) + y_off)
+#define GET_VALUE(_x, _y) (LE16_TO_CPU(*(GLushort*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
+#define PUT_VALUE(_x, _y, d) { \
+   GLushort *_ptr = (GLushort*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
+   *_ptr = CPU_TO_LE16(d);								\
+} while (0)
 #else
 #define GET_PTR(X,Y) radeon_ptr_2byte_8x2(rrb, (X) + x_off, (Y) + y_off)
 #endif
@@ -643,7 +674,11 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_ARGB4444_REV
 #define TAG2(x,y) radeon##x##_ARGB4444_REV##y
 #if defined(RADEON_R600)
-#define GET_PTR(X,Y) r600_ptr_color(rrb, (X) + x_off, (Y) + y_off)
+#define GET_VALUE(_x, _y) (LE16_TO_CPU(*(GLushort*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
+#define PUT_VALUE(_x, _y, d) { \
+   GLushort *_ptr = (GLushort*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
+   *_ptr = CPU_TO_LE16(d);								\
+} while (0)
 #else
 #define GET_PTR(X,Y) radeon_ptr_2byte_8x2(rrb, (X) + x_off, (Y) + y_off)
 #endif
@@ -657,10 +692,10 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_xRGB8888
 #define TAG2(x,y) radeon##x##_xRGB8888##y
 #if defined(RADEON_R600)
-#define GET_VALUE(_x, _y) ((*(GLuint*)(r600_ptr_color(rrb, _x + x_off, _y + y_off)) | 0xff000000))
+#define GET_VALUE(_x, _y) ((LE32_TO_CPU(*(GLuint*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))) | 0xff000000))
 #define PUT_VALUE(_x, _y, d) { \
    GLuint *_ptr = (GLuint*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
-   *_ptr = d;								\
+   *_ptr = CPU_TO_LE32(d);								\
 } while (0)
 #else
 #define GET_VALUE(_x, _y) ((*(GLuint*)(radeon_ptr_4byte(rrb, _x + x_off, _y + y_off)) | 0xff000000))
@@ -679,10 +714,10 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_ARGB8888
 #define TAG2(x,y) radeon##x##_ARGB8888##y
 #if defined(RADEON_R600)
-#define GET_VALUE(_x, _y) (*(GLuint*)(r600_ptr_color(rrb, _x + x_off, _y + y_off)))
+#define GET_VALUE(_x, _y) (LE32_TO_CPU(*(GLuint*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
 #define PUT_VALUE(_x, _y, d) { \
    GLuint *_ptr = (GLuint*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
-   *_ptr = d;								\
+   *_ptr = CPU_TO_LE32(d);								\
 } while (0)
 #else
 #define GET_VALUE(_x, _y) (*(GLuint*)(radeon_ptr_4byte(rrb, _x + x_off, _y + y_off)))
@@ -701,10 +736,10 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_BGRx8888
 #define TAG2(x,y) radeon##x##_BGRx8888##y
 #if defined(RADEON_R600)
-#define GET_VALUE(_x, _y) ((*(GLuint*)(r600_ptr_color(rrb, _x + x_off, _y + y_off)) | 0x000000ff))
+#define GET_VALUE(_x, _y) ((LE32_TO_CPU(*(GLuint*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))) | 0x000000ff))
 #define PUT_VALUE(_x, _y, d) { \
    GLuint *_ptr = (GLuint*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
-   *_ptr = d;								\
+   *_ptr = CPU_TO_LE32(d);								\
 } while (0)
 #else
 #define GET_VALUE(_x, _y) ((*(GLuint*)(radeon_ptr_4byte(rrb, _x + x_off, _y + y_off)) | 0x000000ff))
@@ -723,7 +758,11 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
 #define TAG(x)    radeon##x##_BGRA8888
 #define TAG2(x,y) radeon##x##_BGRA8888##y
 #if defined(RADEON_R600)
-#define GET_PTR(X,Y) r600_ptr_color(rrb, (X) + x_off, (Y) + y_off)
+#define GET_VALUE(_x, _y) (LE32_TO_CPU(*(GLuint*)(r600_ptr_color(rrb, _x + x_off, _y + y_off))))
+#define PUT_VALUE(_x, _y, d) { \
+   GLuint *_ptr = (GLuint*)r600_ptr_color( rrb, _x + x_off, _y + y_off );		\
+   *_ptr = CPU_TO_LE32(d);								\
+} while (0)
 #else
 #define GET_PTR(X,Y) radeon_ptr_4byte(rrb, (X) + x_off, (Y) + y_off)
 #endif
@@ -752,7 +791,7 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
    *(GLushort *)r200_depth_2byte(rrb, _x + x_off, _y + y_off) = d
 #elif defined(RADEON_R600)
 #define WRITE_DEPTH( _x, _y, d )					\
-   *(GLushort *)r600_ptr_depth(rrb, _x + x_off, _y + y_off) = d
+   *(GLushort *)r600_ptr_depth(rrb, _x + x_off, _y + y_off) = CPU_TO_LE16(d)
 #else
 #define WRITE_DEPTH( _x, _y, d )					\
    *(GLushort *)radeon_ptr_2byte_8x2(rrb, _x + x_off, _y + y_off) = d
@@ -763,7 +802,7 @@ static GLubyte *radeon_ptr_2byte_8x2(const struct radeon_renderbuffer * rrb,
    d = *(GLushort *)r200_depth_2byte(rrb, _x + x_off, _y + y_off)
 #elif defined(RADEON_R600)
 #define READ_DEPTH( d, _x, _y )						\
-   d = *(GLushort *)r600_ptr_depth(rrb, _x + x_off, _y + y_off)
+   d = LE16_TO_CPU(*(GLushort *)r600_ptr_depth(rrb, _x + x_off, _y + y_off))
 #else
 #define READ_DEPTH( d, _x, _y )						\
    d = *(GLushort *)radeon_ptr_2byte_8x2(rrb, _x + x_off, _y + y_off)
@@ -792,10 +831,10 @@ do {									\
 #define WRITE_DEPTH( _x, _y, d )					\
 do {									\
    GLuint *_ptr = (GLuint*)r600_ptr_depth( rrb, _x + x_off, _y + y_off );		\
-   GLuint tmp = *_ptr;				\
+   GLuint tmp = LE32_TO_CPU(*_ptr);				\
    tmp &= 0xff000000;							\
    tmp |= ((d) & 0x00ffffff);					\
-   *_ptr = tmp;					\
+   *_ptr = CPU_TO_LE32(tmp);					\
 } while (0)
 #elif defined(RADEON_R200)
 #define WRITE_DEPTH( _x, _y, d )					\
@@ -825,7 +864,7 @@ do {									\
 #elif defined(RADEON_R600)
 #define READ_DEPTH( d, _x, _y )						\
   do {									\
-    d = (*(GLuint*)(r600_ptr_depth(rrb, _x + x_off, _y + y_off)) & 0x00ffffff); \
+    d = (LE32_TO_CPU(*(GLuint*)(r600_ptr_depth(rrb, _x + x_off, _y + y_off))) & 0x00ffffff); \
   }while(0)
 #elif defined(RADEON_R200)
 #define READ_DEPTH( d, _x, _y )						\
@@ -858,15 +897,15 @@ do {									\
 #define WRITE_DEPTH( _x, _y, d )					\
 do {									\
    GLuint *_ptr = (GLuint*)r600_ptr_depth( rrb, _x + x_off, _y + y_off );		\
-   GLuint tmp = *_ptr;				\
+   GLuint tmp = LE32_TO_CPU(*_ptr);				\
    tmp &= 0xff000000;							\
    tmp |= ((d) & 0x00ffffff);					\
-   *_ptr = tmp;					\
+   *_ptr = CPU_TO_LE32(tmp);					\
    _ptr = (GLuint*)r600_ptr_stencil(rrb, _x + x_off, _y + y_off);		\
-   tmp = *_ptr;				\
+   tmp = LE32_TO_CPU(*_ptr);				\
    tmp &= 0xffffff00;							\
    tmp |= ((d) >> 24) & 0xff;						\
-   *_ptr = tmp;					\
+   *_ptr = CPU_TO_LE32(tmp);					\
 } while (0)
 #elif defined(RADEON_R200)
 #define WRITE_DEPTH( _x, _y, d )					\
@@ -891,8 +930,8 @@ do {									\
 #elif defined(RADEON_R600)
 #define READ_DEPTH( d, _x, _y )						\
   do { \
-    d = (*(GLuint*)(r600_ptr_depth(rrb, _x + x_off, _y + y_off))) & 0x00ffffff; \
-    d |= ((*(GLuint*)(r600_ptr_stencil(rrb, _x + x_off, _y + y_off))) << 24) & 0xff000000; \
+    d = (LE32_TO_CPU(*(GLuint*)(r600_ptr_depth(rrb, _x + x_off, _y + y_off))) & 0x00ffffff); \
+    d |= ((LE32_TO_CPU(*(GLuint*)(r600_ptr_stencil(rrb, _x + x_off, _y + y_off))) << 24) & 0xff000000); \
   }while(0)
 #elif defined(RADEON_R200)
 #define READ_DEPTH( d, _x, _y )						\
@@ -927,10 +966,10 @@ do {									\
 #define WRITE_STENCIL( _x, _y, d )					\
 do {									\
    GLuint *_ptr = (GLuint*)r600_ptr_stencil(rrb, _x + x_off, _y + y_off);		\
-   GLuint tmp = *_ptr;				\
+   GLuint tmp = LE32_TO_CPU(*_ptr);				\
    tmp &= 0xffffff00;							\
    tmp |= (d) & 0xff;							\
-   *_ptr = tmp;					\
+   *_ptr = CPU_TO_LE32(tmp);					\
 } while (0)
 #elif defined(RADEON_R200)
 #define WRITE_STENCIL( _x, _y, d )					\
@@ -963,7 +1002,7 @@ do {									\
 #define READ_STENCIL( d, _x, _y )					\
 do {									\
    GLuint *_ptr = (GLuint*)r600_ptr_stencil( rrb, _x + x_off, _y + y_off );		\
-   GLuint tmp = *_ptr;				\
+   GLuint tmp = LE32_TO_CPU(*_ptr);				\
    d = tmp & 0x000000ff;						\
 } while (0)
 #elif defined(RADEON_R200)