[Beignet] [PATCH] utests: added for optimization negtiveAdd

the negtive Add is like: exp -a llvm transfer it to: add x -a, 0 exp x Signed-off-by: rander.wang --- kernels/compiler_remove_negtiveAdd.cl | 4 utests/CMakeLists.txt | 3 ++-

Re: [Beignet] [PATCH 1/2] Backend: Add optimization for negtive modifier

LGTM. Thanks -Original Message- From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of rander.wang Sent: Wednesday, May 17, 2017 16:21 To: beig...@freedesktop.org Cc: Wang, Rander Subject: [Beignet] [PATCH 1/2] Backend: Add optimization for

[Beignet] [PATCH] backend: add sqrt-div pattern to instruction select

there some patterns like: sqrt r1, r2; load r4, 1.0; ===> rqrt r3, r2 div r3, r4, r1; Signed-off-by: rander.wang --- backend/src/backend/gen_insn_selection.cpp | 77 ++ 1 file changed, 77 insertions(+) diff --git

[Beignet] [PATCH] utests: add utest for sqrt-div optimization

Signed-off-by: rander.wang --- kernels/compiler_sqrtDiv.cl | 8 ++ utests/CMakeLists.txt | 3 ++- utests/compiler_sqrtDiv.cpp | 61 + 3 files changed, 71 insertions(+), 1 deletion(-) create mode 100644

Re: [Beignet] [PATCH] backend: add sqrt-div pattern to instruction select

I discuss with Yang Rong, and found you can do more merge for sqrt r1, r2; load r4, 2.0; ===> rqrt r5, r2 div r3, r4, r1; mul r3, r5, 2.0 To get less loadi. -Original Message- From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of

[Beignet] [PATCH] backend: add sqrt-div pattern to instruction select

there some patterns like: sqrt r1, r2; load r4, 1.0; ===> rqrt r3, r2 div r3, r4, r1; Signed-off-by: rander.wang --- backend/src/backend/gen_insn_selection.cpp | 68 ++ 1 file changed, 68 insertions(+) diff --git