Ilia Mirkin
2014-May-20 23:39 UTC
[Nouveau] [PATCH 00/12] Cherry-pick nv50/nvc0 patches from gallium-nine
I went through the gallium-nine tree and picked out nouveau patches that are general bug-fixes. The first bunch I'd like to also get into 10.2. I've reviewed all of them and they make sense to me, but sending them out for public review as well in case there are any objections. Unless I hear objections, I'd like to push this by Friday. Christoph Bumiller (11): nv50,nvc0: always pull out bufctx on context destruction nv50: setup scissors on clear_render_target/depth_stencil nv50,nvc0: set constbufs dirty on pipe context switch nv50/ir/tgsi: TGSI_OPCODE_POW replicates its result nv50/ir/opt: fix constant folding with saturate modifier nv50/ir: fix lowering of predicated instructions (without defs) nv50/ir/tgsi: optimize KIL nv50,nvc0: handle guard band defines nv50,nvc0: allow 15,16,30 bpp display formats nvc0: use PRIxPTR for sizeof() nvc0: assert that we have vertex elements state Joakim Sindholt (1): nv50: count wrapped textures towards the tex_obj count .../drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 11 ++++++++++- .../nouveau/codegen/nv50_ir_lowering_nv50.cpp | 5 ++++- .../drivers/nouveau/codegen/nv50_ir_peephole.cpp | 4 +++- src/gallium/drivers/nouveau/nv50/nv50_context.c | 7 ++----- src/gallium/drivers/nouveau/nv50/nv50_formats.c | 8 ++++---- src/gallium/drivers/nouveau/nv50/nv50_miptree.c | 2 ++ src/gallium/drivers/nouveau/nv50/nv50_screen.c | 10 ++++++++-- .../drivers/nouveau/nv50/nv50_state_validate.c | 4 ++++ src/gallium/drivers/nouveau/nv50/nv50_surface.c | 20 ++++++++++++++++++-- src/gallium/drivers/nouveau/nvc0/nvc0_context.c | 9 +++++---- src/gallium/drivers/nouveau/nvc0/nvc0_program.c | 2 +- src/gallium/drivers/nouveau/nvc0/nvc0_screen.c | 10 ++++++++-- .../drivers/nouveau/nvc0/nvc0_state_validate.c | 1 + src/gallium/drivers/nouveau/nvc0/nvc0_vbo.c | 1 + 14 files changed, 71 insertions(+), 23 deletions(-) -- 1.8.5.5
Ilia Mirkin
2014-May-20 23:39 UTC
[Nouveau] [PATCH 01/12] nv50, nvc0: always pull out bufctx on context destruction
From: Christoph Bumiller <christoph.bumiller at speed.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.2" <mesa-stable at lists.freedesktop.org>
---
src/gallium/drivers/nouveau/nv50/nv50_context.c | 7 ++-----
src/gallium/drivers/nouveau/nvc0/nvc0_context.c | 9 +++++----
2 files changed, 7 insertions(+), 9 deletions(-)
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_context.c
b/src/gallium/drivers/nouveau/nv50/nv50_context.c
index 52e14bf..f844592 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_context.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_context.c
@@ -122,12 +122,9 @@ nv50_destroy(struct pipe_context *pipe)
{
struct nv50_context *nv50 = nv50_context(pipe);
- if (nv50_context_screen(nv50)->cur_ctx == nv50) {
- nv50->base.pushbuf->kick_notify = NULL;
+ if (nv50_context_screen(nv50)->cur_ctx == nv50)
nv50_context_screen(nv50)->cur_ctx = NULL;
- nouveau_pushbuf_bufctx(nv50->base.pushbuf, NULL);
- }
- /* need to flush before destroying the bufctx */
+ nouveau_pushbuf_bufctx(nv50->base.pushbuf, NULL);
nouveau_pushbuf_kick(nv50->base.pushbuf,
nv50->base.pushbuf->channel);
nv50_context_unreference_resources(nv50);
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_context.c
b/src/gallium/drivers/nouveau/nvc0/nvc0_context.c
index 83c8c34..e5040c4 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_context.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_context.c
@@ -123,11 +123,12 @@ nvc0_destroy(struct pipe_context *pipe)
{
struct nvc0_context *nvc0 = nvc0_context(pipe);
- if (nvc0->screen->cur_ctx == nvc0) {
- nvc0->base.pushbuf->kick_notify = NULL;
+ if (nvc0->screen->cur_ctx == nvc0)
nvc0->screen->cur_ctx = NULL;
- nouveau_pushbuf_bufctx(nvc0->base.pushbuf, NULL);
- }
+ /* Unset bufctx, we don't want to revalidate any resources after the
flush.
+ * Other contexts will always set their bufctx again on action calls.
+ */
+ nouveau_pushbuf_bufctx(nvc0->base.pushbuf, NULL);
nouveau_pushbuf_kick(nvc0->base.pushbuf,
nvc0->base.pushbuf->channel);
nvc0_context_unreference_resources(nvc0);
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:39 UTC
[Nouveau] [PATCH 02/12] nv50: setup scissors on clear_render_target/depth_stencil
From: Christoph Bumiller <e0425955 at student.tuwien.ac.at>
[imirkin: add logic to also clear the "regular" scissors]
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.2" <mesa-stable at lists.freedesktop.org>
---
src/gallium/drivers/nouveau/nv50/nv50_surface.c | 20 ++++++++++++++++++--
1 file changed, 18 insertions(+), 2 deletions(-)
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_surface.c
b/src/gallium/drivers/nouveau/nv50/nv50_surface.c
index 1f37527..6e68fb8 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_surface.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_surface.c
@@ -288,6 +288,14 @@ nv50_clear_render_target(struct pipe_context *pipe,
PUSH_REFN(push, bo, mt->base.domain | NOUVEAU_BO_WR);
+ BEGIN_NV04(push, NV50_3D(SCREEN_SCISSOR_HORIZ), 2);
+ PUSH_DATA (push, ( width << 16) | dstx);
+ PUSH_DATA (push, (height << 16) | dsty);
+ BEGIN_NV04(push, NV50_3D(SCISSOR_HORIZ(0)), 2);
+ PUSH_DATA (push, 8192 << 16);
+ PUSH_DATA (push, 8192 << 16);
+ nv50->scissors_dirty |= 1;
+
BEGIN_NV04(push, NV50_3D(RT_CONTROL), 1);
PUSH_DATA (push, 1);
BEGIN_NV04(push, NV50_3D(RT_ADDRESS_HIGH(0)), 5);
@@ -325,7 +333,7 @@ nv50_clear_render_target(struct pipe_context *pipe,
(z << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT));
}
- nv50->dirty |= NV50_NEW_FRAMEBUFFER;
+ nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR;
}
static void
@@ -364,6 +372,14 @@ nv50_clear_depth_stencil(struct pipe_context *pipe,
PUSH_REFN(push, bo, mt->base.domain | NOUVEAU_BO_WR);
+ BEGIN_NV04(push, NV50_3D(SCREEN_SCISSOR_HORIZ), 2);
+ PUSH_DATA (push, ( width << 16) | dstx);
+ PUSH_DATA (push, (height << 16) | dsty);
+ BEGIN_NV04(push, NV50_3D(SCISSOR_HORIZ(0)), 2);
+ PUSH_DATA (push, 8192 << 16);
+ PUSH_DATA (push, 8192 << 16);
+ nv50->scissors_dirty |= 1;
+
BEGIN_NV04(push, NV50_3D(ZETA_ADDRESS_HIGH), 5);
PUSH_DATAh(push, bo->offset + sf->offset);
PUSH_DATA (push, bo->offset + sf->offset);
@@ -390,7 +406,7 @@ nv50_clear_depth_stencil(struct pipe_context *pipe,
(z << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT));
}
- nv50->dirty |= NV50_NEW_FRAMEBUFFER;
+ nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR;
}
void
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:39 UTC
[Nouveau] [PATCH 03/12] nv50, nvc0: set constbufs dirty on pipe context switch
From: Christoph Bumiller <christoph.bumiller at speed.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.2" <mesa-stable at lists.freedesktop.org>
---
src/gallium/drivers/nouveau/nv50/nv50_state_validate.c | 4 ++++
src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c | 1 +
2 files changed, 5 insertions(+)
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_state_validate.c
b/src/gallium/drivers/nouveau/nv50/nv50_state_validate.c
index 18451c7..1dcb961 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_state_validate.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_state_validate.c
@@ -400,6 +400,10 @@ nv50_switch_pipe_context(struct nv50_context *ctx_to)
ctx_to->viewports_dirty = ~0;
ctx_to->scissors_dirty = ~0;
+ ctx_to->constbuf_dirty[0] + ctx_to->constbuf_dirty[1] +
ctx_to->constbuf_dirty[2] = (1 << NV50_MAX_PIPE_CONSTBUFS) - 1;
+
if (!ctx_to->vertex)
ctx_to->dirty &= ~(NV50_NEW_VERTEX | NV50_NEW_ARRAYS);
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
b/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
index 40016fc..dcec910 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_state_validate.c
@@ -531,6 +531,7 @@ nvc0_switch_pipe_context(struct nvc0_context *ctx_to)
for (s = 0; s < 5; ++s) {
ctx_to->samplers_dirty[s] = ~0;
ctx_to->textures_dirty[s] = ~0;
+ ctx_to->constbuf_dirty[s] = (1 << NVC0_MAX_PIPE_CONSTBUFS) - 1;
}
if (!ctx_to->vertex)
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:39 UTC
[Nouveau] [PATCH 04/12] nv50/ir/tgsi: TGSI_OPCODE_POW replicates its result
From: Christoph Bumiller <christoph.bumiller at speed.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.2" <mesa-stable at lists.freedesktop.org>
---
src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
index 3e44bf9..e24be51 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
@@ -2199,7 +2199,6 @@ Converter::handleInstruction(const struct
tgsi_full_instruction *insn)
case TGSI_OPCODE_IMUL_HI:
case TGSI_OPCODE_UMUL_HI:
case TGSI_OPCODE_OR:
- case TGSI_OPCODE_POW:
case TGSI_OPCODE_SHL:
case TGSI_OPCODE_ISHR:
case TGSI_OPCODE_USHR:
@@ -2254,6 +2253,11 @@ Converter::handleInstruction(const struct
tgsi_full_instruction *insn)
FOR_EACH_DST_ENABLED_CHANNEL(0, c, tgsi)
mkOp1(OP_MOV, TYPE_U32, dst0[c], fetchSrc(0, c));
break;
+ case TGSI_OPCODE_POW:
+ val0 = mkOp2v(op, TYPE_F32, getScratch(), fetchSrc(0, 0), fetchSrc(1,
0));
+ FOR_EACH_DST_ENABLED_CHANNEL(0, c, tgsi)
+ mkOp1(OP_MOV, TYPE_F32, dst0[c], val0);
+ break;
case TGSI_OPCODE_EX2:
case TGSI_OPCODE_LG2:
val0 = mkOp1(op, TYPE_F32, getScratch(), fetchSrc(0, 0))->getDef(0);
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:39 UTC
[Nouveau] [PATCH 05/12] nv50/ir/opt: fix constant folding with saturate modifier
From: Christoph Bumiller <e0425955 at student.tuwien.ac.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.2" <mesa-stable at lists.freedesktop.org>
---
src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index e6f8f69..1a2c2e6 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -561,7 +561,7 @@ ConstantFolding::expr(Instruction *i,
if (i->src(0).getImmediate(src0))
expr(i, src0, *i->getSrc(1)->asImm());
} else {
- i->op = OP_MOV;
+ i->op = i->saturate ? OP_SAT : OP_MOV; /* SAT handled by unary() */
}
}
@@ -612,6 +612,7 @@ ConstantFolding::unary(Instruction *i, const ImmediateValue
&imm)
switch (i->op) {
case OP_NEG: res.data.f32 = -imm.reg.data.f32; break;
case OP_ABS: res.data.f32 = fabsf(imm.reg.data.f32); break;
+ case OP_SAT: res.data.f32 = CLAMP(imm.reg.data.f32, 0.0f, 1.0f); break;
case OP_RCP: res.data.f32 = 1.0f / imm.reg.data.f32; break;
case OP_RSQ: res.data.f32 = 1.0f / sqrtf(imm.reg.data.f32); break;
case OP_LG2: res.data.f32 = log2f(imm.reg.data.f32); break;
@@ -922,6 +923,7 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue
&imm0, int s)
case OP_ABS:
case OP_NEG:
+ case OP_SAT:
case OP_LG2:
case OP_RCP:
case OP_SQRT:
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:40 UTC
[Nouveau] [PATCH 06/12] nv50/ir: fix lowering of predicated instructions (without defs)
From: Christoph Bumiller <e0425955 at student.tuwien.ac.at>
Note that predicated instructions with defs are still not supported
because transformation to SSA doesn't handle them yet.
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.2" <mesa-stable at lists.freedesktop.org>
---
src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
index 0fb7666..ed06def 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp
@@ -1279,8 +1279,11 @@ NV50LoweringPreSSA::checkPredicate(Instruction *insn)
Value *pred = insn->getPredicate();
Value *cdst;
- if (!pred || pred->reg.file == FILE_FLAGS)
+ // FILE_PREDICATE will simply be changed to FLAGS on conversion to SSA
+ if (!pred ||
+ pred->reg.file == FILE_FLAGS || pred->reg.file == FILE_PREDICATE)
return;
+
cdst = bld.getSSA(1, FILE_FLAGS);
bld.mkCmp(OP_SET, CC_NEU, insn->dType, cdst, insn->dType,
bld.loadImm(NULL, 0), pred);
--
1.8.5.5
From: Christoph Bumiller <e0425955 at student.tuwien.ac.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.2" <mesa-stable at lists.freedesktop.org>
---
src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
index e24be51..a0f1fe1 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp
@@ -2457,7 +2457,12 @@ Converter::handleInstruction(const struct
tgsi_full_instruction *insn)
break;
case TGSI_OPCODE_KILL_IF:
val0 = new_LValue(func, FILE_PREDICATE);
+ mask = 0;
for (c = 0; c < 4; ++c) {
+ const int s = tgsi.getSrc(0).getSwizzle(c);
+ if (mask & (1 << s))
+ continue;
+ mask |= 1 << s;
mkCmp(OP_SET, CC_LT, TYPE_F32, val0, TYPE_F32, fetchSrc(0, c), zero);
mkOp(OP_DISCARD, TYPE_NONE, NULL)->setPredicate(CC_P, val0);
}
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:40 UTC
[Nouveau] [PATCH 08/12] nv50,nvc0: handle guard band defines
From: Christoph Bumiller <christoph.bumiller at speed.at>
[imirkin: moved default case out of switch]
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
src/gallium/drivers/nouveau/nv50/nv50_screen.c | 10 ++++++++--
src/gallium/drivers/nouveau/nvc0/nvc0_screen.c | 10 ++++++++--
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_screen.c
b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
index 68d30ea..36a4ad1 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_screen.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
@@ -286,10 +286,16 @@ nv50_screen_get_paramf(struct pipe_screen *pscreen, enum
pipe_capf param)
return 16.0f;
case PIPE_CAPF_MAX_TEXTURE_LOD_BIAS:
return 4.0f;
- default:
- NOUVEAU_ERR("unknown PIPE_CAP %d\n", param);
+ case PIPE_CAPF_GUARD_BAND_LEFT:
+ case PIPE_CAPF_GUARD_BAND_TOP:
return 0.0f;
+ case PIPE_CAPF_GUARD_BAND_RIGHT:
+ case PIPE_CAPF_GUARD_BAND_BOTTOM:
+ return 0.0f; /* that or infinity */
}
+
+ NOUVEAU_ERR("unknown PIPE_CAPF %d\n", param);
+ return 0.0f;
}
static void
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
index cccfe2b..9f89f31 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
@@ -294,10 +294,16 @@ nvc0_screen_get_paramf(struct pipe_screen *pscreen, enum
pipe_capf param)
return 16.0f;
case PIPE_CAPF_MAX_TEXTURE_LOD_BIAS:
return 15.0f;
- default:
- NOUVEAU_ERR("unknown PIPE_CAP %d\n", param);
+ case PIPE_CAPF_GUARD_BAND_LEFT:
+ case PIPE_CAPF_GUARD_BAND_TOP:
return 0.0f;
+ case PIPE_CAPF_GUARD_BAND_RIGHT:
+ case PIPE_CAPF_GUARD_BAND_BOTTOM:
+ return 0.0f; /* that or infinity */
}
+
+ NOUVEAU_ERR("unknown PIPE_CAPF %d\n", param);
+ return 0.0f;
}
static int
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:40 UTC
[Nouveau] [PATCH 09/12] nv50, nvc0: allow 15, 16, 30 bpp display formats
From: Christoph Bumiller <christoph.bumiller at speed.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
src/gallium/drivers/nouveau/nv50/nv50_formats.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_formats.c
b/src/gallium/drivers/nouveau/nv50/nv50_formats.c
index 3af34c1..ff33654 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_formats.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_formats.c
@@ -194,9 +194,9 @@ const struct nv50_format
nv50_format_table[PIPE_FORMAT_COUNT] SXB(S8X24_UINT, C0, S8_Z24, T),
SXB(X32_S8X24_UINT, C1, Z32_S8_X24, T),
- F3B(B5G6R5_UNORM, B5G6R5_UNORM, C2, C1, C0, xx, UNORM, 5_6_5, T),
- C4B(B5G5R5A1_UNORM, BGR5_A1_UNORM, C2, C1, C0, C3, UNORM, 5_5_5_1, TB),
- F3B(B5G5R5X1_UNORM, BGR5_X1_UNORM, C2, C1, C0, xx, UNORM, 5_5_5_1, TB),
+ F3B(B5G6R5_UNORM, B5G6R5_UNORM, C2, C1, C0, xx, UNORM, 5_6_5, TD),
+ C4B(B5G5R5A1_UNORM, BGR5_A1_UNORM, C2, C1, C0, C3, UNORM, 5_5_5_1, TD),
+ F3B(B5G5R5X1_UNORM, BGR5_X1_UNORM, C2, C1, C0, xx, UNORM, 5_5_5_1, TD),
C4B(B4G4R4A4_UNORM, NONE, C2, C1, C0, C3, UNORM, 4_4_4_4, T),
F3B(B4G4R4X4_UNORM, NONE, C2, C1, C0, xx, UNORM, 4_4_4_4, T),
F3B(R9G9B9E5_FLOAT, NONE, C0, C1, C2, xx, FLOAT, 9_9_9_E5, T),
@@ -204,7 +204,7 @@ const struct nv50_format
nv50_format_table[PIPE_FORMAT_COUNT] C4A(R10G10B10A2_UNORM, RGB10_A2_UNORM,
C0, C1, C2, C3, UNORM, 10_10_10_2,
IBV, 0),
C4A(B10G10R10A2_UNORM, BGR10_A2_UNORM, C2, C1, C0, C3, UNORM, 10_10_10_2,
- TBV, 1),
+ TDV, 1),
C4A(R10G10B10A2_SNORM, NONE, C0, C1, C2, C3, SNORM, 10_10_10_2, TV, 0),
C4A(B10G10R10A2_SNORM, NONE, C2, C1, C0, C3, SNORM, 10_10_10_2, TV, 1),
C4A(R10G10B10A2_UINT, RGB10_A2_UINT, C0, C1, C2, C3, UINT, 10_10_10_2, TRV,
0),
--
1.8.5.5
From: Christoph Bumiller <christoph.bumiller at speed.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
src/gallium/drivers/nouveau/nvc0/nvc0_program.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
b/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
index 1d59fc4..8724cc5 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_program.c
@@ -512,7 +512,7 @@ nvc0_program_dump(struct nvc0_program *prog)
if (prog->type != PIPE_SHADER_COMPUTE) {
for (pos = 0; pos < sizeof(prog->hdr) / sizeof(prog->hdr[0]);
++pos)
- debug_printf("HDR[%02lx] = 0x%08x\n",
+ debug_printf("HDR[%02"PRIxPTR"] = 0x%08x\n",
pos * sizeof(prog->hdr[0]), prog->hdr[pos]);
}
debug_printf("shader binary code (0x%x bytes):",
prog->code_size);
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:40 UTC
[Nouveau] [PATCH 11/12] nvc0: assert that we have vertex elements state
From: Christoph Bumiller <christoph.bumiller at speed.at>
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
src/gallium/drivers/nouveau/nvc0/nvc0_vbo.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_vbo.c
b/src/gallium/drivers/nouveau/nvc0/nvc0_vbo.c
index c58d6da..83d406d 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_vbo.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_vbo.c
@@ -423,6 +423,7 @@ nvc0_vertex_arrays_validate(struct nvc0_context *nvc0)
nouveau_bufctx_reset(nvc0->bufctx_3d, NVC0_BIND_VTX);
+ assert(vertex);
if (unlikely(vertex->need_conversion) ||
unlikely(nvc0->vertprog->vp.edgeflag < PIPE_MAX_ATTRIBS)) {
vbo_mode = 3;
--
1.8.5.5
Ilia Mirkin
2014-May-20 23:40 UTC
[Nouveau] [PATCH 12/12] nv50: count wrapped textures towards the tex_obj count
From: Joakim Sindholt <opensource at zhasha.com>
But don't count their size towards the allocated memory, since that
belongs to whoever created it.
Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
src/gallium/drivers/nouveau/nv50/nv50_miptree.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_miptree.c
b/src/gallium/drivers/nouveau/nv50/nv50_miptree.c
index 513d8f9..4c55179 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_miptree.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_miptree.c
@@ -404,6 +404,8 @@ nv50_miptree_from_handle(struct pipe_screen *pscreen,
mt->level[0].offset = 0;
mt->level[0].tile_mode = mt->base.bo->config.nv50.tile_mode;
+ NOUVEAU_DRV_STAT(nouveau_screen(pscreen), tex_obj_current_count, 1);
+
/* no need to adjust bo reference count */
return &mt->base.base;
}
--
1.8.5.5
Emil Velikov
2014-May-21 18:51 UTC
[Nouveau] [Mesa-dev] [PATCH 04/12] nv50/ir/tgsi: TGSI_OPCODE_POW replicates its result
On 21/05/14 00:39, Ilia Mirkin wrote:> From: Christoph Bumiller <christoph.bumiller at speed.at> > > Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> > Cc: "10.2" <mesa-stable at lists.freedesktop.org> > --- > src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 6 +++++- > 1 file changed, 5 insertions(+), 1 deletion(-) > > diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp > index 3e44bf9..e24be51 100644 > --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp > +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp > @@ -2199,7 +2199,6 @@ Converter::handleInstruction(const struct tgsi_full_instruction *insn) > case TGSI_OPCODE_IMUL_HI: > case TGSI_OPCODE_UMUL_HI: > case TGSI_OPCODE_OR: > - case TGSI_OPCODE_POW: > case TGSI_OPCODE_SHL: > case TGSI_OPCODE_ISHR: > case TGSI_OPCODE_USHR: > @@ -2254,6 +2253,11 @@ Converter::handleInstruction(const struct tgsi_full_instruction *insn) > FOR_EACH_DST_ENABLED_CHANNEL(0, c, tgsi) > mkOp1(OP_MOV, TYPE_U32, dst0[c], fetchSrc(0, c)); > break; > + case TGSI_OPCODE_POW: > + val0 = mkOp2v(op, TYPE_F32, getScratch(), fetchSrc(0, 0), fetchSrc(1, 0)); > + FOR_EACH_DST_ENABLED_CHANNEL(0, c, tgsi) > + mkOp1(OP_MOV, TYPE_F32, dst0[c], val0); > + break;Can you use mkMov ? Pretty please :) -Emil> case TGSI_OPCODE_EX2: > case TGSI_OPCODE_LG2: > val0 = mkOp1(op, TYPE_F32, getScratch(), fetchSrc(0, 0))->getDef(0); >
Emil Velikov
2014-May-21 18:57 UTC
[Nouveau] [Mesa-dev] [PATCH 02/12] nv50: setup scissors on clear_render_target/depth_stencil
On 21/05/14 00:39, Ilia Mirkin wrote:> From: Christoph Bumiller <e0425955 at student.tuwien.ac.at> > > [imirkin: add logic to also clear the "regular" scissors]Can you please share why are you've added the "regular" scissors ? Does it matter if we set the screen scissors before the render target params? Thanks Emil> Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> > Cc: "10.2" <mesa-stable at lists.freedesktop.org> > --- > src/gallium/drivers/nouveau/nv50/nv50_surface.c | 20 ++++++++++++++++++-- > 1 file changed, 18 insertions(+), 2 deletions(-) > > diff --git a/src/gallium/drivers/nouveau/nv50/nv50_surface.c b/src/gallium/drivers/nouveau/nv50/nv50_surface.c > index 1f37527..6e68fb8 100644 > --- a/src/gallium/drivers/nouveau/nv50/nv50_surface.c > +++ b/src/gallium/drivers/nouveau/nv50/nv50_surface.c > @@ -288,6 +288,14 @@ nv50_clear_render_target(struct pipe_context *pipe, > > PUSH_REFN(push, bo, mt->base.domain | NOUVEAU_BO_WR); > > + BEGIN_NV04(push, NV50_3D(SCREEN_SCISSOR_HORIZ), 2); > + PUSH_DATA (push, ( width << 16) | dstx); > + PUSH_DATA (push, (height << 16) | dsty); > + BEGIN_NV04(push, NV50_3D(SCISSOR_HORIZ(0)), 2); > + PUSH_DATA (push, 8192 << 16); > + PUSH_DATA (push, 8192 << 16); > + nv50->scissors_dirty |= 1; > + > BEGIN_NV04(push, NV50_3D(RT_CONTROL), 1); > PUSH_DATA (push, 1); > BEGIN_NV04(push, NV50_3D(RT_ADDRESS_HIGH(0)), 5); > @@ -325,7 +333,7 @@ nv50_clear_render_target(struct pipe_context *pipe, > (z << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT)); > } > > - nv50->dirty |= NV50_NEW_FRAMEBUFFER; > + nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR; > } > > static void > @@ -364,6 +372,14 @@ nv50_clear_depth_stencil(struct pipe_context *pipe, > > PUSH_REFN(push, bo, mt->base.domain | NOUVEAU_BO_WR); > > + BEGIN_NV04(push, NV50_3D(SCREEN_SCISSOR_HORIZ), 2); > + PUSH_DATA (push, ( width << 16) | dstx); > + PUSH_DATA (push, (height << 16) | dsty); > + BEGIN_NV04(push, NV50_3D(SCISSOR_HORIZ(0)), 2); > + PUSH_DATA (push, 8192 << 16); > + PUSH_DATA (push, 8192 << 16); > + nv50->scissors_dirty |= 1; > + > BEGIN_NV04(push, NV50_3D(ZETA_ADDRESS_HIGH), 5); > PUSH_DATAh(push, bo->offset + sf->offset); > PUSH_DATA (push, bo->offset + sf->offset); > @@ -390,7 +406,7 @@ nv50_clear_depth_stencil(struct pipe_context *pipe, > (z << NV50_3D_CLEAR_BUFFERS_LAYER__SHIFT)); > } > > - nv50->dirty |= NV50_NEW_FRAMEBUFFER; > + nv50->dirty |= NV50_NEW_FRAMEBUFFER | NV50_NEW_SCISSOR; > } > > void >
Possibly Parallel Threads
- [Mesa-dev] [PATCH 04/12] nv50/ir/tgsi: TGSI_OPCODE_POW replicates its result
- [Mesa-dev] [PATCH 04/12] nv50/ir/tgsi: TGSI_OPCODE_POW replicates its result
- [Mesa-dev] [PATCH 04/12] nv50/ir/tgsi: TGSI_OPCODE_POW replicates its result
- [Mesa-dev] [PATCH 04/12] nv50/ir/tgsi: TGSI_OPCODE_POW replicates its result
- [PATCH] nv50/ir: saturate FRC result to avoid completely bogus values