| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | glsl: Rewrite and fix min/max to saturate optimization. | Matt Turner | 2015-02-27 | 1 | -29/+46 |
| * | glsl: Don't optimize min/max into saturate when EmitNoSat is set | Abdiel Janulgue | 2014-12-08 | 1 | -1/+1 |
| * | glsl: Optimize scalar all_equal/any_nequal into equal/nequal. | Matt Turner | 2014-12-05 | 1 | -0/+10 |
| * | glsl: Remove now useless dot optimization on basis vect | Matt Turner | 2014-11-03 | 1 | -23/+0 |
| * | glsl: Emit mul instead of dot if only one component left. | Matt Turner | 2014-11-03 | 1 | -1/+4 |
| * | glsl: Drop constant 0.0 components from dot products. | Matt Turner | 2014-10-29 | 1 | -0/+27 |
| * | glsl: Recognize open-coded pow(x, y). | Matt Turner | 2014-09-27 | 1 | -0/+14 |
| * | glsl: Optimize clamp(x, b, 1.0), where b > 0.0 as max(saturate(x),b) | Abdiel Janulgue | 2014-08-31 | 1 | -0/+23 |
| * | glsl: Optimize clamp(x, 0.0, b), where b < 1.0 as min(saturate(x),b) | Abdiel Janulgue | 2014-08-31 | 1 | -0/+39 |
| * | glsl: Optimize clamp(x, 0, 1) as saturate(x) | Abdiel Janulgue | 2014-08-31 | 1 | -0/+36 |
| * | glsl: Don't convert reductions of ivec to a dot-product | Ian Romanick | 2014-06-25 | 1 | -1/+3 |
| * | glsl: Optimize (v.x + v.y) + (v.z + v.w) into dot(v, 1.0). | Matt Turner | 2014-06-19 | 1 | -0/+46 |
| * | glsl: Pass in options to do_algebraic(). | Matt Turner | 2014-06-19 | 1 | -3/+8 |
| * | glsl: Pass ctx->Const.NativeIntegers to do_algebraic. | Kenneth Graunke | 2014-04-08 | 1 | -3/+5 |
| * | glsl: Optimize (x + y cmp 0) into (x cmp -y). | Matt Turner | 2014-04-05 | 1 | -0/+22 |
| * | glsl: Optimize pow(x, 2) into x * x. | Matt Turner | 2014-03-18 | 1 | -0/+8 |
| * | glsl: Fix broken LRP algebraic optimization. | Kenneth Graunke | 2014-03-02 | 1 | -1/+3 |
| * | glsl: Optimize lrp(x, 0, a) into x - (x * a). | Matt Turner | 2014-02-28 | 1 | -0/+2 |
| * | glsl: Optimize lrp(0, y, a) into y * a. | Matt Turner | 2014-02-28 | 1 | -0/+2 |
| * | glsl: Optimize triop_csel with all-true or all-false. | Eric Anholt | 2014-02-07 | 1 | -0/+7 |
| * | glsl: Optimize various cases of fma (aka MAD). | Eric Anholt | 2014-02-07 | 1 | -0/+13 |
| * | glsl: Optimize lrp(x, x, coefficient) --> x. | Eric Anholt | 2014-02-07 | 1 | -0/+2 |
| * | glsl: Optimize pow(x, 1) -> x. | Eric Anholt | 2014-02-07 | 1 | -0/+4 |
| * | glsl: Optimize log(exp(x)) and exp(log(x)) into x. | Eric Anholt | 2014-02-07 | 1 | -0/+36 |
| * | glsl: Optimize ~~x into x. | Eric Anholt | 2014-02-07 | 1 | -0/+5 |
| * | glsl: Optimize open-coded lrp into lrp. | Jordan Justen | 2014-01-21 | 1 | -0/+52 |
| * | glsl: Optimize pow(2, x) --> exp2(x). | Kenneth Graunke | 2014-01-07 | 1 | -0/+11 |
| * | glsl: Optimize pow(1.0, X) --> 1.0. | Kenneth Graunke | 2014-01-07 | 1 | -0/+6 |
| * | glsl: Apply the transformation "1/rsq(x) == sqrt(x)" in opt_algebraic. | Eric Anholt | 2013-11-15 | 1 | -3/+4 |
| * | glsl: Apply the transformation "(a ^^ a) -> false" in opt_algebraic. | Eric Anholt | 2013-11-15 | 1 | -1/+3 |
| * | glsl: Apply the transformation "(a && a) -> a" in opt_algebraic. | Eric Anholt | 2013-11-15 | 1 | -1/+3 |
| * | glsl: Apply the transformation "(a || a) -> a" in opt_algebraic. | Eric Anholt | 2013-11-15 | 1 | -1/+3 |
| * | glsl: Drop no-op shifts involving 0. | Eric Anholt | 2013-10-28 | 1 | -0/+10 |
| * | glsl: Use ir_builder more in opt_algebraic. | Eric Anholt | 2013-10-28 | 1 | -30/+10 |
| * | glsl: Move common code out of opt_algebraic's handle_expression(). | Eric Anholt | 2013-10-28 | 1 | -78/+39 |
| * | glsl: Optimize (not A) and (not B) into not (A or B). | Matt Turner | 2013-10-25 | 1 | -0/+9 |
| * | glsl: Optimize (not A) or (not B) into not (A and B). | Matt Turner | 2013-10-25 | 1 | -0/+12 |
| * | glsl: Optimize -(-expr) into expr. | Matt Turner | 2013-10-21 | 1 | -0/+10 |
| * | glsl: Optimize abs(-expr) and abs(abs(expr)) into abs(expr). | Matt Turner | 2013-10-21 | 1 | -0/+18 |
| * | glsl: Use saved values instead of recomputing them. | Matt Turner | 2013-10-21 | 1 | -8/+4 |
| * | glsl: Optimize mul(a, -1) into neg(a). | Matt Turner | 2013-10-16 | 1 | -0/+23 |
| * | glsl: Add support for new bit built-ins in ARB_gpu_shader5. | Matt Turner | 2013-05-06 | 1 | -3/+3 |
| * | glsl: Optimize ir_triop_lrp(x, y, a) with a = 0.0f or 1.0f | Matt Turner | 2013-02-28 | 1 | -0/+11 |
| * | glsl: Convert mix() to use a new ir_triop_lrp opcode. | Kenneth Graunke | 2013-02-28 | 1 | -3/+3 |
| * | glsl: Transform dot product by a basis vector into a swizzle | Matt Turner | 2012-06-12 | 1 | -0/+24 |
| * | glsl: Check for zero vectors in ir_binop_dot | Matt Turner | 2012-06-12 | 1 | -0/+7 |
| * | glsl: Put a bunch of optimization visitors under anonymous namespaces. | Eric Anholt | 2012-06-11 | 1 | -0/+4 |
| * | Convert everything from the talloc API to the ralloc API. | Kenneth Graunke | 2011-01-31 | 1 | -1/+1 |
| * | glsl: fix matrix type check in ir_algebraic | Aras Pranckevicius | 2010-11-30 | 1 | -2/+2 |
| * | glsl: Add ir_quadop_vector expression | Ian Romanick | 2010-11-19 | 1 | -1/+1 |
