[Mesa-dev] [PATCH] R600: Emit CF_ALU and use true kcache register.
Vadim Girlin
vadimgirlin at gmail.com
Thu Mar 28 12:54:41 PDT 2013
On 03/28/2013 09:47 PM, Vincent Lejeune wrote:
> [snip]
> diff --git a/lib/Target/R600/R600RegisterInfo.td b/lib/Target/R600/R600RegisterInfo.td
> index ce5994c..3ee6623 100644
> --- a/lib/Target/R600/R600RegisterInfo.td
> +++ b/lib/Target/R600/R600RegisterInfo.td
> @@ -43,6 +43,37 @@ foreach Index = 0-127 in {
> Index>;
> }
>
> +// KCACHE_BANK0
> +foreach Index = 159-128 in {
> + foreach Chan = [ "X", "Y", "Z", "W" ] in {
> + // 32-bit Temporary Registers
> + def KC0_#Index#_#Chan : R600RegWithChan <"KC0["#Index#"-128]."#Chan, Index, Chan>;
> + }
> + // 128-bit Temporary Registers
> + def KC0_#Index#_XYZW : R600Reg_128 <"KC0["#Index#"-128].XYZW",
> + [!cast<Register>("KC0_"#Index#"_X"),
> + !cast<Register>("KC0_"#Index#"_Y"),
> + !cast<Register>("KC0_"#Index#"_Z"),
> + !cast<Register>("KC0_"#Index#"_W")],
> + Index>;
> +}
> +
> +// KCACHE_BANK1
> +foreach Index = 191-159 in {
Probably 160 should be used instead of 159 here (and in the two
occurrences below)?
Vadim
> + foreach Chan = [ "X", "Y", "Z", "W" ] in {
> + // 32-bit Temporary Registers
> + def KC1_#Index#_#Chan : R600RegWithChan <"KC1["#Index#"-159]."#Chan, Index, Chan>;
> + }
> + // 128-bit Temporary Registers
> + def KC1_#Index#_XYZW : R600Reg_128 <"KC1["#Index#"-159].XYZW",
> + [!cast<Register>("KC1_"#Index#"_X"),
> + !cast<Register>("KC1_"#Index#"_Y"),
> + !cast<Register>("KC1_"#Index#"_Z"),
> + !cast<Register>("KC1_"#Index#"_W")],
> + Index>;
> +}
> +
> +
> // Array Base Register holding input in FS
> foreach Index = 448-480 in {
> def ArrayBase#Index : R600Reg<"ARRAY_BASE", Index>;
> @@ -80,6 +111,38 @@ def R600_Addr : RegisterClass <"AMDGPU", [i32], 127, (add (sequence "Addr%u_X",
>
> } // End isAllocatable = 0
>
> +def R600_KC0_X : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC0_%u_X", 128, 159))>;
> +
> +def R600_KC0_Y : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC0_%u_Y", 128, 159))>;
> +
> +def R600_KC0_Z : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC0_%u_Z", 128, 159))>;
> +
> +def R600_KC0_W : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC0_%u_W", 128, 159))>;
> +
> +def R600_KC0 : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (interleave R600_KC0_X, R600_KC0_Y,
> + R600_KC0_Z, R600_KC0_W)>;
> +
> +def R600_KC1_X : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC1_%u_X", 160, 191))>;
> +
> +def R600_KC1_Y : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC1_%u_Y", 160, 191))>;
> +
> +def R600_KC1_Z : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC1_%u_Z", 160, 191))>;
> +
> +def R600_KC1_W : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (add (sequence "KC1_%u_W", 160, 191))>;
> +
> +def R600_KC1 : RegisterClass <"AMDGPU", [f32, i32], 32,
> + (interleave R600_KC1_X, R600_KC1_Y,
> + R600_KC1_Z, R600_KC1_W)>;
> +
> def R600_TReg32_X : RegisterClass <"AMDGPU", [f32, i32], 32,
> (add (sequence "T%u_X", 0, 127), AR_X)>;
>
> diff --git a/test/CodeGen/R600/kcache-fold.ll b/test/CodeGen/R600/kcache-fold.ll
> index e8e2bf5..3d70e4b 100644
> --- a/test/CodeGen/R600/kcache-fold.ll
> +++ b/test/CodeGen/R600/kcache-fold.ll
> @@ -1,7 +1,7 @@
> ;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
>
> ; CHECK: @main1
> -; CHECK: MOV T{{[0-9]+\.[XYZW], CBuf0\[[0-9]+\]\.[XYZW]}}
> +; CHECK: MOV T{{[0-9]+\.[XYZW], KC0}}
> define void @main1() {
> main_body:
> %0 = load <4 x float> addrspace(8)* null
>
More information about the mesa-dev
mailing list