[Mesa-dev] [PATCH 01/12] R600/structurizer: add class to find the Nearest Common Dominator

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 66 ++ 1 file changed, 66 insertions(+) diff --git a/lib/Target/R600/AMDGPUStructurizeCFG.cpp b/lib/Target/R600/AMDGPUStructurizeCFG.cpp index c4c9762..86cb04a

[Mesa-dev] [PATCH 03/12] R600/structurizer: improve finding condition values

From: Christian König Using the new NearestCommonDominator class. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 31 +- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/lib/Target/R600/AMDGPUStructurizeCFG.cpp b/lib

[Mesa-dev] [PATCH 04/12] R600/structurizer: improve loop handling

From: Christian König Generate more than one loop if it seems to make sense. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 344 +- 1 file changed, 148 insertions(+), 196 deletions(-) diff --git a/lib/Target/R600

[Mesa-dev] [PATCH 05/12] R600/structurizer: improve inverting conditions

From: Christian König Stop adding more instructions than necessary. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 40 +- 1 file changed, 39 insertions(+), 1 deletion(-) diff --git a/lib/Target/R600/AMDGPUStructurizeCFG.cpp b/lib

[Mesa-dev] [PATCH 06/12] R600/SI: remove some more unused code

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/AMDGPUCodeEmitter.h| 45 lib/Target/R600/MCTargetDesc/AMDGPUMCCodeEmitter.h |7 --- 2 files changed, 52 deletions(-) delete mode 100644 lib/Target/R600/AMDGPUCodeEmitter.h diff

[Mesa-dev] [PATCH 07/12] R600/SI: move *_Helper definitions to SIInstrFormat.td

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 66 + lib/Target/R600/SIInstrInfo.td| 66 - 2 files changed, 66 insertions(+), 66 deletions(-) diff --git a/lib/Target

[Mesa-dev] [PATCH 08/12] R600/SI: fix VOPC encoding v2

From: Christian König Previously it only worked because of coincident. v2: fix 64bit versions, use 0x80 (inline 0) instead of SGPR0 for the unused SRC2 Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 53 +++-- 1 file changed, 16

[Mesa-dev] [PATCH 09/12] R600/SI: replace AllReg_* with [SV]Src_* v2

From: Christian König Mark all the operands that can also have an immediate. v2: SOFFSET is also an SSrc_32 operand Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 36 +-- lib/Target/R600/SIInstructions.td | 128 ++--- lib

[Mesa-dev] [PATCH 10/12] R600/SI: cleanup literal handling v2

From: Christian König Seems to be allot simpler, and also paves the way for further improvements. v2: rebased on master, use 0 in BUFFER_LOAD_FORMAT_XYZW, use VGPR0 in dummy EXP, avoid compiler warning, break after encoding the first literal. Signed-off-by: Christian König --- lib

[Mesa-dev] [PATCH 11/12] R600/SI: nuke SReg_1 v2

From: Christian König It's completely unnecessary and can be replace with proper SReg_64 handling instead. This actually fixes a piglit test on SI. v2: use correct register class in addRegisterClass, set special classes as not allocatable Signed-off-by: Christian König --- lib/T

[Mesa-dev] [PATCH 12/12] R600/SI: Add pattern to simplify i64 loading

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td|4 lib/Target/R600/SIInstructions.td |5 + 2 files changed, 9 insertions(+) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target/R600/SIInstrInfo.td index efc6015..8c4e5af 100644

Re: [Mesa-dev] r600g: status of my work on the shader optimization

Am 14.02.2013 12:05, schrieb Henri Verbeet: On 14 February 2013 11:42, Christian König wrote: nice work, I think you've made quite a progress here, but on the other hand it should be clear that the LLVM backend is the future and we should concentrate on that. I'm not sure that

Re: [Mesa-dev] [PATCH 01/12] R600/structurizer: add class to find the Nearest Common Dominator

Please ignore this version of the patchset, it was send accidentally from the wrong machine and so doesn't contain the correct patches. Christian. Am 14.02.2013 11:42, schrieb Christian König: From: Christian König Signed-off-by: Christian König --- lib/Target

Re: [Mesa-dev] [PATCH 10/12] R600/SI: cleanup literal handling v2

Am 14.02.2013 15:14, schrieb Michel Dänzer: On Don, 2013-02-14 at 14:35 +0100, Michel Dänzer wrote: On Don, 2013-02-14 at 11:43 +0100, Christian König wrote: +// Only one literal allowed +break; The same literal could be used for several operands though. :) Basically, it seems like

[Mesa-dev] [PATCH 03/12] R600/structurizer: improve finding condition values

From: Christian König Using the new NearestCommonDominator class. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 31 +- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/lib/Target/R600/AMDGPUStructurizeCFG.cpp b/lib

[Mesa-dev] [PATCH 02/12] R600/structurizer: improve PHI value finding

From: Christian König Using the new NearestCommonDominator class. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp |6 ++ 1 file changed, 6 insertions(+) diff --git a/lib/Target/R600/AMDGPUStructurizeCFG.cpp b/lib/Target/R600/AMDGPUStructurizeCFG.cpp index

[Mesa-dev] [PATCH 01/12] R600/structurizer: add class to find the Nearest Common Dominator

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 66 ++ 1 file changed, 66 insertions(+) diff --git a/lib/Target/R600/AMDGPUStructurizeCFG.cpp b/lib/Target/R600/AMDGPUStructurizeCFG.cpp index c4c9762..86cb04a

[Mesa-dev] [PATCH 04/12] R600/structurizer: improve loop handling

From: Christian König Generate more than one loop if it seems to make sense. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 344 +- 1 file changed, 148 insertions(+), 196 deletions(-) diff --git a/lib/Target/R600

[Mesa-dev] [PATCH 05/12] R600/structurizer: improve inverting conditions

From: Christian König Stop adding more instructions than necessary. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUStructurizeCFG.cpp | 40 +- 1 file changed, 39 insertions(+), 1 deletion(-) diff --git a/lib/Target/R600/AMDGPUStructurizeCFG.cpp b/lib

[Mesa-dev] [PATCH 06/12] R600/SI: remove some more unused code

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/AMDGPUCodeEmitter.h| 45 lib/Target/R600/MCTargetDesc/AMDGPUMCCodeEmitter.h |7 --- 2 files changed, 52 deletions(-) delete mode 100644 lib/Target/R600/AMDGPUCodeEmitter.h diff

[Mesa-dev] [PATCH 07/12] R600/SI: move *_Helper definitions to SIInstrFormat.td

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 66 + lib/Target/R600/SIInstrInfo.td| 66 - 2 files changed, 66 insertions(+), 66 deletions(-) diff --git a/lib/Target

[Mesa-dev] [PATCH 08/12] R600/SI: fix VOPC encoding v2

From: Christian König Previously it only worked because of coincident. v2: fix 64bit versions, use 0x80 (inline 0) instead of SGPR0 for the unused SRC2 Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 53 +++-- 1 file changed, 16

[Mesa-dev] [PATCH 09/12] R600/SI: replace AllReg_* with [SV]Src_* v2

From: Christian König Mark all the operands that can also have an immediate. v2: SOFFSET is also an SSrc_32 operand Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 36 +-- lib/Target/R600/SIInstructions.td | 128 ++--- lib

[Mesa-dev] [PATCH 10/12] R600/SI: cleanup literal handling v3

From: Christian König Seems to be allot simpler, and also paves the way for further improvements. v2: rebased on master, use 0 in BUFFER_LOAD_FORMAT_XYZW, use VGPR0 in dummy EXP, avoid compiler warning, break after encoding the first literal. v3: correctly use V_ADD_F32_e64 Signed-off

[Mesa-dev] [PATCH 11/12] R600/SI: nuke SReg_1 v3

From: Christian König It's completely unnecessary and can be replace with proper SReg_64 handling instead. This actually fixes a piglit test on SI. v2: use correct register class in addRegisterClass, set special classes as not allocatable v3: revert setting special classes a

[Mesa-dev] [PATCH 12/12] R600/SI: Add pattern to simplify i64 loading

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td|4 lib/Target/R600/SIInstructions.td |5 + 2 files changed, 9 insertions(+) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target/R600/SIInstrInfo.td index efc6015..8c4e5af 100644

Re: [Mesa-dev] [PATCH v3] R600/SI: Fix int_SI_fs_interp_constant

V_INTERP_MOV_F32 instead of hardcoding it there, and add a special operand class for the parameter slots for type checking and pretty printing. NOTE: This is a candidate for the Mesa stable branch. Signed-off-by: Michel Dänzer Reviewed-by: Christian König --- v3: Use operand class instead of register

Re: [Mesa-dev] r600g: status of my work on the shader optimization

Am 15.02.2013 12:00, schrieb Vadim Girlin: On 02/14/2013 02:42 PM, Christian König wrote: Hi Vadim, nice work, I think you've made quite a progress here, but on the other hand it should be clear that the LLVM backend is the future and we should concentrate on that. "LLVM back

Re: [Mesa-dev] r600g: status of my work on the shader optimization

Am 15.02.2013 22:25, schrieb Vadim Girlin: On 02/15/2013 03:22 PM, Christian König wrote: Am 15.02.2013 12:00, schrieb Vadim Girlin: [SNIP] Heaven 3.0, all settings high/enabled, 1280x720, HD5750: default backend : 20.0 fps llvm backend: 18.8 fps r600-sb : 38.0 fps Quite

Re: [Mesa-dev] [PATCH] radeonsi: Fix blending using destination alpha factor but non-alpha destination

Am 18.02.2013 20:11, schrieb Roland Scheidegger: Am 18.02.2013 19:14, schrieb Michel Dänzer: From: Michel Dänzer 11 more little piglits. NOTE: This is a candidate for the 9.1 branch. Signed-off-by: Michel Dänzer --- Any ideas why this seems necessary with radeonsi but not with r600g? Mayb

[Mesa-dev] [PATCH 3/8] R600/SI: rework VOP2_* pattern

From: Christian König Fixing asm operation names. Signed-off-by: Christian König --- lib/Target/R600/SIISelLowering.cpp |3 --- lib/Target/R600/SIInstrInfo.td | 37 ++-- 2 files changed, 18 insertions(+), 22 deletions(-) diff --git a/lib/Target/R600

[Mesa-dev] [PATCH 2/8] R600/SI: rework VOP1_* patterns

From: Christian König Fixing asm operation names. Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td | 36 ++-- 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target/R600/SIInstrInfo.td

[Mesa-dev] [PATCH 4/8] R600/SI: simplify VOPC_* patterns

From: Christian König Fixing asm operation names. Signed-off-by: Christian König --- lib/Target/R600/AMDGPUInstructions.td |5 + lib/Target/R600/SIInstrInfo.td| 19 +- lib/Target/R600/SIInstructions.td | 444 +++-- 3 files changed, 213 insertions

[Mesa-dev] [PATCH 1/8] R600/SI: cleanup SIInstrInfo.td and SIInstrFormat.td

From: Christian König Those two files got mixed up. Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 500 +++-- lib/Target/R600/SIInstrInfo.td| 495 +++- 2 files changed, 509 insertions(+), 486

[Mesa-dev] [PATCH 5/8] R600/SI: sort and cleanup SIInstrInfo.td

From: Christian König Fix code formating and sort/group the classes. Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td | 100 +++- 1 file changed, 58 insertions(+), 42 deletions(-) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target

[Mesa-dev] [PATCH 6/8] R600/SI: use patterns for clamp, fabs, fneg

From: Christian König Instead of using custom inserters, it's simpler and should make DAG folding easier. Signed-off-by: Christian König --- lib/Target/R600/SIISelLowering.cpp | 36 lib/Target/R600/SIInstructions.td | 26 ++--

[Mesa-dev] [PATCH 7/8] R600/SI: add OMOD patterns

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/AMDGPUInstructions.td | 15 +++ lib/Target/R600/SIInstructions.td | 18 ++ 2 files changed, 33 insertions(+) diff --git a/lib/Target/R600/AMDGPUInstructions.td b/lib/Target/R600

[Mesa-dev] [PATCH 8/8] R600/SI: replace SI_V_CNDLT with a pattern

From: Christian König It actually fixes quite a bunch of piglit tests. Signed-off-by: Christian König --- lib/Target/R600/SIISelLowering.cpp | 22 -- lib/Target/R600/SIISelLowering.h |2 -- lib/Target/R600/SIInstructions.td | 12 +--- 3 files changed, 5

[Mesa-dev] [PATCH 08/14] R600/SI: add the missing M*BUF|IMG asm operands

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td | 12 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target/R600/SIInstrInfo.td index 56ca03a..99168ce 100644 --- a/lib/Target/R600

[Mesa-dev] [PATCH 07/14] R600/SI: add the missing S_* asm operands

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td | 52 ++-- 1 file changed, 34 insertions(+), 18 deletions(-) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target/R600/SIInstrInfo.td index 05325db..56ca03a 100644

[Mesa-dev] [PATCH 02/14] R600/SI: add constant for inline zero operand

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td |7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target/R600/SIInstrInfo.td index cf0d5b9..8b90d45 100644 --- a/lib/Target/R600

[Mesa-dev] [PATCH 03/14] R600/SI: rework VOP1_* patterns v2

From: Christian König Fixing asm operation names. v2: use ZERO constant, also add asm operands Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td | 38 +- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/lib/Target/R600

[Mesa-dev] [PATCH 11/14] R600/SI: add OMOD patterns

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/AMDGPUInstructions.td | 15 +++ lib/Target/R600/SIInstructions.td | 18 ++ 2 files changed, 33 insertions(+) diff --git a/lib/Target/R600/AMDGPUInstructions.td b/lib/Target/R600

[Mesa-dev] [PATCH 05/14] R600/SI: simplify VOPC_* pattern v2

From: Christian König Fixing asm operation names. v2: fix name of the e64 encoding, also add asm operands Signed-off-by: Christian König --- lib/Target/R600/AMDGPUInstructions.td |5 + lib/Target/R600/SIInstrInfo.td| 23 +- lib/Target/R600/SIInstructions.td | 444

[Mesa-dev] [PATCH 06/14] R600/SI: rework VOP3 classes

From: Christian König Order the classes and add asm operands. Signed-off-by: Christian König --- lib/Target/R600/SIInstrInfo.td | 28 ++-- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/lib/Target/R600/SIInstrInfo.td b/lib/Target/R600/SIInstrInfo.td

[Mesa-dev] [PATCH 09/14] R600/SI: add all the other missing asm operands

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/InstPrinter/AMDGPUInstPrinter.cpp |4 ++ lib/Target/R600/SIInstructions.td | 45 +++-- 2 files changed, 28 insertions(+), 21 deletions(-) diff --git a/lib/Target/R600/InstPrinter

[Mesa-dev] [PATCH 13/14] R600/SI: replace IMPLICIT_DEF with SIOperand.ZERO

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstructions.td |2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td index c1c7851..71ae33b 100644 --- a/lib/Target/R600

[Mesa-dev] [PATCH 10/14] R600/SI: use patterns for clamp, fabs, fneg

From: Christian König Instead of using custom inserters, it's simpler and should make DAG folding easier. Signed-off-by: Christian König --- lib/Target/R600/SIISelLowering.cpp | 36 lib/Target/R600/SIInstructions.td | 26 ++--

[Mesa-dev] [PATCH 14/14] R600/SI: inline V_ADD|SUB_F32 patterns

From: Christian König Signed-off-by: Christian König --- lib/Target/R600/SIInstructions.td | 14 +- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td index 71ae33b..9ea26d2 100644 --- a/lib/Target

[Mesa-dev] [PATCH 01/14] R600/SI: cleanup SIInstrInfo.td and SIInstrFormat.td

From: Christian König Those two files got mixed up. Signed-off-by: Christian König --- lib/Target/R600/SIInstrFormats.td | 500 +-- lib/Target/R600/SIInstrInfo.td| 515 - 2 files changed, 527 insertions(+), 488

[Mesa-dev] [PATCH 04/14] R600/SI: rework VOP2_* pattern v2

From: Christian König Fixing asm operation names. v2: use ZERO constant, also add asm operands Signed-off-by: Christian König --- lib/Target/R600/SIISelLowering.cpp |3 --- lib/Target/R600/SIInstrInfo.td | 37 ++-- 2 files changed, 19 insertions

[Mesa-dev] [PATCH 12/14] R600/SI: replace SI_V_CNDLT with a pattern

From: Christian König It actually fixes quite a bunch of piglit tests. This is a candidate for the mesa-stable branch. Signed-off-by: Christian König --- lib/Target/R600/SIISelLowering.cpp | 22 -- lib/Target/R600/SIISelLowering.h |2 -- lib/Target/R600

Re: [Mesa-dev] [PATCH 11/14] R600/SI: add OMOD patterns

Am 21.02.2013 09:26, schrieb Michel Dänzer: On Mit, 2013-02-20 at 18:46 +0100, Christian König wrote: diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td index 833e6cd..7c157e9 100644 --- a/lib/Target/R600/SIInstructions.td +++ b/lib/Target/R600

Re: [Mesa-dev] [PATCH 09/14] R600/SI: add all the other missing asm operands

Am 21.02.2013 09:39, schrieb Michel Dänzer: On Mit, 2013-02-20 at 18:46 +0100, Christian König wrote: diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td index 700b8f8..866c7cb 100644 --- a/lib/Target/R600/SIInstructions.td +++ b/lib/Target/R600/SIInstructions.td

Re: [Mesa-dev] [PATCH] vl: Fix off-by-one error in device_name_length allocation.

Am 22.02.2013 07:44, schrieb Vinson Lee: Fixes out-of-bounds write reported by Coverity. Signed-off-by: Vinson Lee Reviewed-by: Christian König --- src/gallium/auxiliary/vl/vl_winsys_dri.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/gallium/auxiliary/vl

Re: [Mesa-dev] [PATCH 1/2] st/vdpau: Fix memory leak in vlVdpOutputSurfaceCreate.

Am 22.02.2013 07:25, schrieb Vinson Lee: Fixes resource leak defect reported by Coverity. Signed-off-by: Vinson Lee Reviewed-by: Christian König --- src/gallium/state_trackers/vdpau/output.c | 1 + 1 file changed, 1 insertion(+) diff --git a/src/gallium/state_trackers/vdpau/output.c b

Re: [Mesa-dev] [PATCH] st/xvmc/tests: Ensure colorkey is initialized.

Am 22.02.2013 07:18, schrieb Vinson Lee: Fixes uninitialized scalar variable defect reported by Coverity. Signed-off-by: Vinson Lee Reviewed-by: Christian König --- src/gallium/state_trackers/xvmc/tests/xvmc_bench.c | 4 1 file changed, 4 insertions(+) diff --git a/src/gallium

Re: [Mesa-dev] [PATCH 1/3] radeonsi: Refactor packing of texture coordinates

Am 22.02.2013 17:02, schrieb Michel Dänzer: From: Michel Dänzer The number of coordinates to pack will be useful for other address parameters as well. Signed-off-by: Michel Dänzer Very nice, for this series: Reviewed-by: Christian König --- src/gallium/drivers/radeonsi

[Mesa-dev] [PATCH 7/7] radeon/llvm: enable LICM and DCE pass

From: Christian König Signed-off-by: Christian König --- .../drivers/radeon/radeon_setup_tgsi_llvm.c|2 ++ 1 file changed, 2 insertions(+) diff --git a/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c b/src/gallium/drivers/radeon/radeon_setup_tgsi_llvm.c index f7b7586..f017b87

[Mesa-dev] [PATCH 6/7] radeonsi: add LLVMNoUnwindAttribute to intrinsic

From: Christian König So LLVM can better eliminate dead code. Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c |2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.c b/src/gallium/drivers/radeonsi

[Mesa-dev] [PATCH 1/7] radeonsi: switch to v*i8 for resources and samplers

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c | 31 +--- 1 file changed, 12 insertions(+), 19 deletions(-) diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.c b/src/gallium/drivers/radeonsi

[Mesa-dev] [PATCH 1/7] radeonsi: switch to v*i8 for resources and samplers

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c | 31 +--- 1 file changed, 12 insertions(+), 19 deletions(-) diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.c b/src/gallium/drivers/radeonsi

[Mesa-dev] [PATCH 4/7] radeonsi: remove SI.vs.load.buffer.index

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c | 21 +++-- src/gallium/drivers/radeonsi/radeonsi_shader.h |1 + 2 files changed, 12 insertions(+), 10 deletions(-) diff --git a/src/gallium/drivers/radeonsi

[Mesa-dev] [PATCH 2/7] radeon/llvm: replace shader type intrinsic with function attribute

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeon/radeon_llvm_emit.cpp | 22 ++ src/gallium/drivers/radeon/radeon_llvm_emit.h |2 ++ src/gallium/drivers/radeonsi/radeonsi_shader.c | 14 ++ 3 files changed, 26

[Mesa-dev] [PATCH 5/7] radeonsi: rework input interpolation

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c | 88 +++- src/gallium/drivers/radeonsi/radeonsi_shader.h | 18 - 2 files changed, 72 insertions(+), 34 deletions(-) diff --git a/src/gallium/drivers/radeonsi

[Mesa-dev] [PATCH 3/7] radeon/llvm: make SGPRs proper function arguments

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/r600/r600_llvm.c |1 + src/gallium/drivers/radeon/radeon_llvm.h |3 + .../drivers/radeon/radeon_setup_tgsi_llvm.c| 32 +++--- src/gallium/drivers/radeonsi/radeonsi_shader.c

Re: [Mesa-dev] [PATCH 1/7] radeonsi: switch to v*i8 for resources and samplers

Am 05.03.2013 18:18, schrieb Michel Dänzer: On Die, 2013-03-05 at 15:27 +0100, Christian König wrote: From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c | 31 +--- 1 file changed, 12 insertions(+), 19 deletions

Re: [Mesa-dev] [PATCH 7/7] radeon/llvm: enable LICM and DCE pass

loop with an unused variable incremented, the increment depends on itself, but it's completely useless... Christian. - Mail original - De : Michel Dänzer À : Christian König Cc : mesa-dev@lists.freedesktop.org Envoyé le : Mardi 5 mars 2013 18h20 Objet : Re: [Mesa-dev] [PATCH

Re: [Mesa-dev] [PATCH] R600/SI: Use source scheduler

because it ends up trying to spill registers, which we don't support yet (and which is probably a bad idea in general for performance if it can be avoided). NOTE: This is a candidate for the Mesa stable branch. Signed-off-by: Michel Dänzer Reviewed-by: Christian König BTW: I played a

[Mesa-dev] [RFC] Solving the TGSI indirect addressing optimization problem

Hi everybody, this problem has been open for quite some time now, with a bunch of different opinions and sometimes even patches floating on the list. The solutions proposed or implemented so far all more or less incomplete, so this approach was designed in mind with both completeness and compatib

[Mesa-dev] [PATCH 1/7] tgsi/ureg: cleanup local temporary emission

From: Christian König Instead of emitting each temporary separately, emit them in a chunk. Signed-off-by: Christian König --- src/gallium/auxiliary/tgsi/tgsi_ureg.c | 53 ++-- 1 file changed, 17 insertions(+), 36 deletions(-) diff --git a/src/gallium/auxiliary

[Mesa-dev] [PATCH 2/7] tgsi/ureg: implement support for array temporaries

From: Christian König Don't bother with free temporaries, just allocate them at the end and also emit them in their own declaration. Signed-off-by: Christian König --- src/gallium/auxiliary/tgsi/tgsi_ureg.c | 55 src/gallium/auxiliary/tgsi/tgsi_ureg.h |

[Mesa-dev] [PATCH 3/7] glsl_to_tgsi: use get_temp for all allocations

From: Christian König Signed-off-by: Christian König --- src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 23 ++- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp index

[Mesa-dev] [PATCH 4/7] glsl_to_tgsi: allocate arrays separately

From: Christian König Instead of allocating everything as temporaries, use the new array allocation functions. Signed-off-by: Christian König --- src/mesa/main/mtypes.h |1 + src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 83 ++-- 2 files

[Mesa-dev] [PATCH 5/7] glsl_to_tgsi: remove indirect addressing limitations

From: Christian König They shouldn't be necessary any more. Signed-off-by: Christian König --- src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 36 +++- 1 file changed, 3 insertions(+), 33 deletions(-) diff --git a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/src

[Mesa-dev] [PATCH 6/7] tgsi: remove TGSI_FILE_(IMMEDIATE|TEMP)_ARRAY

From: Christian König Nobody seems to be using it, and only nv50 had a partial implementation. Signed-off-by: Christian König --- src/gallium/auxiliary/tgsi/tgsi_build.c| 19 - src/gallium/auxiliary/tgsi/tgsi_dump.c | 38 - src/gallium/auxiliary/tgsi

[Mesa-dev] [PATCH 7/7] tgsi: use separate structure for indirect address

From: Christian König To further improve the optimization of source and destination indirect addressing we need the ability to store a reference to the declaration of the addressed operands. Since most of the fields in tgsi_src_register doesn't apply for an indirect addressing operand re

Re: [Mesa-dev] [RFC] Solving the TGSI indirect addressing optimization problem

Am 11.03.2013 14:47, schrieb Christoph Bumiller: On 11.03.2013 13:44, Christian König wrote: Hi everybody, this problem has been open for quite some time now, with a bunch of different opinions and sometimes even patches floating on the list. Nice, finally someone implements a proper solution

Re: [Mesa-dev] [PATCH 7/7] tgsi: use separate structure for indirect address

wanted to discuss all the details first before proceeding with anything that wouldn't be accepted. A few more remarks inline. - Original Message - From: Christian König To further improve the optimization of source and destination indirect addressing we need the ability to store

Re: [Mesa-dev] [RFC] Solving the TGSI indirect addressing optimization problem

Am 12.03.2013 02:48, schrieb Marek Olšák: On Mon, Mar 11, 2013 at 1:44 PM, Christian König wrote: Hi everybody, this problem has been open for quite some time now, with a bunch of different opinions and sometimes even patches floating on the list. The solutions proposed or implemented so far

Re: [Mesa-dev] [PATCH 7/7] tgsi: use separate structure for indirect address

nd send out the resulting patches for a second round of reviews. A few more remarks inline. - Original Message - From: Christian König To further improve the optimization of source and destination indirect addressing we need the ability to store a reference to the declaration of the a

[Mesa-dev] [PATCH 1/9] tgsi/ureg: cleanup local temporary emission v2

From: Christian König Instead of emitting each temporary separately, emit them in a chunk. v2: keep separate function for emitting temps Signed-off-by: Christian König --- src/gallium/auxiliary/tgsi/tgsi_ureg.c | 30 +- 1 file changed, 13 insertions(+), 17

[Mesa-dev] [PATCH 2/9] tgsi/ureg: implement support for array temporaries

From: Christian König Don't bother with free temporaries, just allocate them at the end and also emit them in their own declaration. Signed-off-by: Christian König --- src/gallium/auxiliary/tgsi/tgsi_ureg.c | 55 src/gallium/auxiliary/tgsi/tgsi_ureg.h |

[Mesa-dev] [PATCH 0/9] Solving the TGSI indirect addressing optimization problem v2

Hello everyone, this is the second round of this patchset. Since the first round I made the following changes to it: 1. Add a new field ArrayID to the declaration instead of relaying on referencing the N-th declaration. 2. Minor bugfix in glsl_to_tgsi and just like temps allocate arrays on first

[Mesa-dev] [PATCH 3/9] glsl_to_tgsi: use get_temp for all allocations

From: Christian König Signed-off-by: Christian König --- src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 23 ++- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/src/mesa/state_tracker/st_glsl_to_tgsi.cpp index

[Mesa-dev] [PATCH 4/9] glsl_to_tgsi: allocate arrays separately v2

From: Christian König Instead of allocating everything as temporaries, use the new array allocation functions. v2: fix bug in simplify_cmp, declare arrays on demand Signed-off-by: Christian König --- src/mesa/main/mtypes.h |1 + src/mesa/state_tracker

[Mesa-dev] [PATCH 5/9] glsl_to_tgsi: remove indirect addressing limitations

From: Christian König They shouldn't be necessary any more. Signed-off-by: Christian König --- src/mesa/state_tracker/st_glsl_to_tgsi.cpp | 36 +++- 1 file changed, 3 insertions(+), 33 deletions(-) diff --git a/src/mesa/state_tracker/st_glsl_to_tgsi.cpp b/src

[Mesa-dev] [PATCH 6/9] tgsi: remove TGSI_FILE_(IMMEDIATE|TEMP)_ARRAY

From: Christian König Nobody seems to be using it, and only nv50 had a partial implementation. Signed-off-by: Christian König --- src/gallium/auxiliary/tgsi/tgsi_build.c| 19 - src/gallium/auxiliary/tgsi/tgsi_dump.c | 38 -- src/gallium/auxiliary/tgsi

[Mesa-dev] [PATCH 7/9] tgsi: add ArrayID to declarations

From: Christian König Remember which declarations are declared as "arrays" and so can be indirectly addressed. ArrayIDs start at 1, cause for compatibility reasons zero is treaded as no array present. Signed-off-by: Christian König --- src/gallium/auxiliary/tgsi/tgsi_dump.c

[Mesa-dev] [PATCH 9/9] tgsi: add ArrayID documentation

From: Christian König Signed-off-by: Christian König --- src/gallium/docs/source/tgsi.rst | 16 1 file changed, 16 insertions(+) diff --git a/src/gallium/docs/source/tgsi.rst b/src/gallium/docs/source/tgsi.rst index d9a7fe9..27fe039 100644 --- a/src/gallium/docs/source

[Mesa-dev] [PATCH 8/9] tgsi: use separate structure for indirect address v2

From: Christian König To further improve the optimization of source and destination indirect addressing we need the ability to store a reference to the declaration of the addressed operands. Since most of the fields in tgsi_src_register doesn't apply for an indirect addressing operand re

[Mesa-dev] [PATCH 1/4] radeon/llvm: rework input fetch and output store

From: Christian König Cleanup the code and implement indirect addressing. Signed-off-by: Christian König --- src/gallium/drivers/radeon/radeon_llvm.h | 32 +-- .../drivers/radeon/radeon_setup_tgsi_llvm.c| 241 +++- 2 files changed, 151 insertions(+), 122

[Mesa-dev] [PATCH 2/4] radeonsi: switch to using resource destribtors for constants

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c | 34 +++- src/gallium/drivers/radeonsi/si_state.c| 32 ++ 2 files changed, 37 insertions(+), 29 deletions(-) diff --git a/src/gallium

[Mesa-dev] [PATCH 4/4] radeonsi: enable indirect adressing

From: Christian König Fixing 16 piglit tests. Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_pipe.c |2 +- src/gallium/drivers/radeonsi/radeonsi_shader.c |5 - 2 files changed, 1 insertion(+), 6 deletions(-) diff --git a/src/gallium/drivers/radeonsi

[Mesa-dev] [PATCH 0/4] Indirect addressing for radeonsi

Hi, as promised here is the mesa part of my indirect addressing patchset for radeonsi. Based on the TGSI changes I've send out earlier today. Please review, Christian. ___ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.

[Mesa-dev] [PATCH 3/4] radeonsi: implement indirect adressing of constants

From: Christian König Signed-off-by: Christian König --- src/gallium/drivers/radeonsi/radeonsi_shader.c | 14 -- 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/src/gallium/drivers/radeonsi/radeonsi_shader.c b/src/gallium/drivers/radeonsi/radeonsi_shader.c index

Re: [Mesa-dev] [PATCH] R600: Relax some vector constraints on Dot4.

Hi Vincent, while I really appreciate your work, I think you're development is going into the wrong direction here. Those copies you're trying to avoid (not only with this patch, but also with the previous REG_SEQUENCE patches), shouldn't happen in the first place. I'm not so deeply into the R

Re: [Mesa-dev] [PATCH 9/9] tgsi: add ArrayID documentation

Am 14.03.2013 15:53, schrieb Christoph Bumiller: On 14.03.2013 15:20, Christian König wrote: From: Christian König Signed-off-by: Christian König --- src/gallium/docs/source/tgsi.rst | 16 1 file changed, 16 insertions(+) diff --git a/src/gallium/docs/source/tgsi.rst b

Re: [Mesa-dev] [PATCH] R600: Relax some vector constraints on Dot4.

registers with this patch. Vincent - Mail original - De : Christian König À : Vincent Lejeune Cc : llvm-comm...@cs.uiuc.edu; mesa-dev@lists.freedesktop.org Envoyé le : Vendredi 15 mars 2013 11h18 Objet : Re: [Mesa-dev] [PATCH] R600: Relax some vector constraints on Dot4. Hi Vincent, while I r

Re: [Mesa-dev] [PATCH 9/9] tgsi: add ArrayID documentation

Am 15.03.2013 18:58, schrieb Christoph Bumiller: On 15.03.2013 13:08, Christian König wrote: Am 14.03.2013 15:53, schrieb Christoph Bumiller: On 14.03.2013 15:20, Christian König wrote: From: Christian König Signed-off-by: Christian König --- src/gallium/docs/source/tgsi.rst | 16

<    1   2   3   4   5   6   7   8   9   10   >