i965/gen7: Set MOCS L3 cacheability for IVB/BYT (v2)

IVB/BYT also has the same L3 cacheability control in MOCS as HSW,
so let's make use of it.

pts/xonotic and pts/reaction @ 1920x1080 gain ~4% on my IVB GT2. Most
other things show less gains/no regressions, except furmark which
loses some 10 points.

I didn't have a BYT at hand for testing.

v2: Don't check (brw->gen == 7) in gen7 functions. (chadv)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>

diff --git a/src/mesa/drivers/dri/i965/brw_draw_upload.c b/src/mesa/drivers/dri/i965/brw_draw_upload.c
index 158c9e5c5fbbb3e8b392c43a3002a9e4cc3bd3ff..390b4a37f35168c41df1d92d97e1cfbb21eb4264 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_draw_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_draw_upload.c
@@ -659,7 +659,7 @@ static void brw_emit_vertices(struct brw_context *brw)
         if (brw->gen >= 7)
            dw0 |= GEN7_VB0_ADDRESS_MODIFYENABLE;
 
-        if (brw->is_haswell)
+         if (brw->gen == 7)
            dw0 |= GEN7_MOCS_L3 << 16;
 
         OUT_BATCH(dw0 | (buffer->stride << BRW_VB0_PITCH_SHIFT));

diff --git a/src/mesa/drivers/dri/i965/brw_misc_state.c b/src/mesa/drivers/dri/i965/brw_misc_state.c
index f24fdaf49004f38c962cc267aa6bb8ab1470e9d1..ac7f1f414fef018b61785e8308b32dbd840ddae8 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_misc_state.c
+++ b/src/mesa/drivers/dri/i965/brw_misc_state.c
@@ -1038,7 +1038,7 @@ static void upload_state_base_address( struct brw_context *brw )
     */
 
    if (brw->gen >= 6) {
-      uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+      uint8_t mocs = brw->gen == 7 ? GEN7_MOCS_L3 : 0;
 
       if (brw->gen == 6)
         intel_emit_post_sync_nonzero_flush(brw);

diff --git a/src/mesa/drivers/dri/i965/gen6_blorp.cpp b/src/mesa/drivers/dri/i965/gen6_blorp.cpp
index b47466abfea2f2c964e4a22c974fcae2682e99e1..1c85921476be2efaf018836767efcef4f79b7126 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen6_blorp.cpp
+++ b/src/mesa/drivers/dri/i965/gen6_blorp.cpp
@@ -74,7 +74,7 @@ void
 gen6_blorp_emit_state_base_address(struct brw_context *brw,
                                    const brw_blorp_params *params)
 {
-   uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+   uint8_t mocs = brw->gen == 7 ? GEN7_MOCS_L3 : 0;
 
    BEGIN_BATCH(10);
    OUT_BATCH(CMD_STATE_BASE_ADDRESS << 16 | (10 - 2));
@@ -168,7 +168,7 @@ gen6_blorp_emit_vertices(struct brw_context *brw,
       if (brw->gen >= 7)
          dw0 |= GEN7_VB0_ADDRESS_MODIFYENABLE;
 
-      if (brw->is_haswell)
+      if (brw->gen == 7)
          dw0 |= GEN7_MOCS_L3 << 16;
 
       BEGIN_BATCH(batch_length);

diff --git a/src/mesa/drivers/dri/i965/gen7_blorp.cpp b/src/mesa/drivers/dri/i965/gen7_blorp.cpp
index 44e75788db4f317f26517966f5920c0a88b3810e..a387836b9f2cca58fda13172dfb1ddc95db6b75b 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_blorp.cpp
+++ b/src/mesa/drivers/dri/i965/gen7_blorp.cpp
@@ -143,7 +143,7 @@ gen7_blorp_emit_surface_state(struct brw_context *brw,
     */
    struct intel_region *region = surface->mt->region;
    uint32_t tile_x, tile_y;
-   uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+   const uint8_t mocs = GEN7_MOCS_L3;
 
    uint32_t tiling = surface->map_stencil_as_y_tiled
       ? I915_TILING_Y : region->tiling;
@@ -616,7 +616,7 @@ gen7_blorp_emit_constant_ps(struct brw_context *brw,
                             const brw_blorp_params *params,
                             uint32_t wm_push_const_offset)
 {
-   uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+   const uint8_t mocs = GEN7_MOCS_L3;
 
    /* Make sure the push constants fill an exact integer number of
     * registers.
@@ -658,7 +658,7 @@ static void
 gen7_blorp_emit_depth_stencil_config(struct brw_context *brw,
                                      const brw_blorp_params *params)
 {
-   uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+   const uint8_t mocs = GEN7_MOCS_L3;
    uint32_t surfwidth, surfheight;
    uint32_t surftype;
    unsigned int depth = MAX2(params->depth.mt->logical_depth0, 1);

diff --git a/src/mesa/drivers/dri/i965/gen7_misc_state.c b/src/mesa/drivers/dri/i965/gen7_misc_state.c
index 51067b3762daee4027f9dd48e3c2a58464cc41c8..eb942cfcafa0c2c838890371bcc3ad28b8b241a3 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_misc_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_misc_state.c
@@ -41,7 +41,7 @@ gen7_emit_depth_stencil_hiz(struct brw_context *brw,
                             uint32_t tile_x, uint32_t tile_y)
 {
    struct gl_context *ctx = &brw->ctx;
-   uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+   const uint8_t mocs = GEN7_MOCS_L3;
    struct gl_framebuffer *fb = ctx->DrawBuffer;
    uint32_t surftype;
    unsigned int depth = 1;

diff --git a/src/mesa/drivers/dri/i965/gen7_vs_state.c b/src/mesa/drivers/dri/i965/gen7_vs_state.c
index 7a6ba59f41557c01e23eb7994c669fdbdb6194d4..64a19fa9d7323d455315381021e7056307dd962f 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_vs_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_vs_state.c
@@ -63,8 +63,6 @@ upload_vs_state(struct brw_context *brw)
       OUT_BATCH(0);
       ADVANCE_BATCH();
    } else {
-      uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
-
       BEGIN_BATCH(7);
       OUT_BATCH(_3DSTATE_CONSTANT_VS << 16 | (7 - 2));
       OUT_BATCH(brw->vs.push_const_size);
@@ -72,7 +70,7 @@ upload_vs_state(struct brw_context *brw)
       /* Pointer to the VS constant buffer.  Covered by the set of
        * state flags from gen6_prepare_wm_contants
        */
-      OUT_BATCH(brw->vs.push_const_offset | mocs);
+      OUT_BATCH(brw->vs.push_const_offset | GEN7_MOCS_L3);
       OUT_BATCH(0);
       OUT_BATCH(0);
       OUT_BATCH(0);

diff --git a/src/mesa/drivers/dri/i965/gen7_wm_state.c b/src/mesa/drivers/dri/i965/gen7_wm_state.c
index ba7a53d8705c15fccc914d7911d8a5374aa7f66d..e88db78f449a9e22348fe5cdb810a4038ab0adf4 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_wm_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_wm_state.c
@@ -141,8 +141,6 @@ upload_ps_state(struct brw_context *brw)
       OUT_BATCH(0);
       ADVANCE_BATCH();
    } else {
-      uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
-
       BEGIN_BATCH(7);
       OUT_BATCH(_3DSTATE_CONSTANT_PS << 16 | (7 - 2));
 
@@ -152,7 +150,7 @@ upload_ps_state(struct brw_context *brw)
       /* Pointer to the WM constant buffer.  Covered by the set of
        * state flags from gen6_upload_wm_push_constants.
        */
-      OUT_BATCH(brw->wm.push_const_offset | mocs);
+      OUT_BATCH(brw->wm.push_const_offset | GEN7_MOCS_L3);
       OUT_BATCH(0);
       OUT_BATCH(0);
       OUT_BATCH(0);

diff --git a/src/mesa/drivers/dri/i965/gen7_wm_surface_state.c b/src/mesa/drivers/dri/i965/gen7_wm_surface_state.c
index cdd2242076d2834677b6820c43b5200dfb1eac54..91f854bd078120426678ce58cd797b27e2b57902 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_wm_surface_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_wm_surface_state.c
@@ -286,7 +286,6 @@ gen7_update_texture_surface(struct gl_context *ctx,
    struct gl_texture_image *firstImage = tObj->Image[0][tObj->BaseLevel];
    struct gl_sampler_object *sampler = _mesa_get_samplerobj(ctx, unit);
    uint32_t tile_x, tile_y;
-   uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
 
    if (tObj->Target == GL_TEXTURE_BUFFER) {
       gen7_update_buffer_texture_surface(ctx, unit, binding_table, surf_index);
@@ -335,7 +334,7 @@ gen7_update_texture_surface(struct gl_context *ctx,
     */
    surf[5] = ((tile_x / 4) << BRW_SURFACE_X_OFFSET_SHIFT |
               (tile_y / 2) << BRW_SURFACE_Y_OFFSET_SHIFT |
-              SET_FIELD(mocs, GEN7_SURFACE_MOCS) |
+              SET_FIELD(GEN7_MOCS_L3, GEN7_SURFACE_MOCS) |
               /* mip count */
               (intelObj->_MaxLevel - tObj->BaseLevel));
 
@@ -514,7 +513,7 @@ gen7_update_renderbuffer_surface(struct brw_context *brw,
    bool is_array = false;
    int depth = MAX2(rb->Depth, 1);
    int min_array_element;
-   uint8_t mocs = brw->is_haswell ? GEN7_MOCS_L3 : 0;
+   const uint8_t mocs = GEN7_MOCS_L3;
    GLenum gl_target = rb->TexImage ?
                          rb->TexImage->TexObject->Target : GL_TEXTURE_2D;