From fb5d38e21982e9eb3195c61d020c9772b73bdbcf Mon Sep 17 00:00:00 2001 From: Patrick Rudolph Date: Mon, 28 Mar 2016 11:52:00 +0200 Subject: r600g: fix and optimize tgsi_cmp when using ABS and NEG modifier Some apps set NEG and ABS on the source param to test for zero. Use ALU_OP3_CNDE insted of ALU_OP3_CNDGE and unset both modifiers. It also removes the need for a MOV instruction, as ABS isn't supported on op3. Tested on AMD CAYMAN and AMD RV770. Signed-off-by: Patrick Rudolph Cc: mesa-stable@lists.freedesktop.org Signed-off-by: Dave Airlie --- src/gallium/drivers/r600/r600_shader.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'src/gallium/drivers/r600') diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c index 64b049a1ced..cd5ae449dee 100644 --- a/src/gallium/drivers/r600/r600_shader.c +++ b/src/gallium/drivers/r600/r600_shader.c @@ -7707,6 +7707,15 @@ static int tgsi_cmp(struct r600_shader_ctx *ctx) int i, r, j; int lasti = tgsi_last_instruction(inst->Dst[0].Register.WriteMask); int temp_regs[3]; + unsigned op; + + if (ctx->src[0].abs && ctx->src[0].neg) { + op = ALU_OP3_CNDE; + ctx->src[0].abs = 0; + ctx->src[0].neg = 0; + } else { + op = ALU_OP3_CNDGE; + } for (j = 0; j < inst->Instruction.NumSrcRegs; j++) { temp_regs[j] = 0; @@ -7719,7 +7728,7 @@ static int tgsi_cmp(struct r600_shader_ctx *ctx) continue; memset(&alu, 0, sizeof(struct r600_bytecode_alu)); - alu.op = ALU_OP3_CNDGE; + alu.op = op; r = tgsi_make_src_for_op3(ctx, temp_regs[0], i, &alu.src[0], &ctx->src[0]); if (r) return r; -- cgit v1.2.3