Files
armorpaint/base/tools/iris.c/iris_vulkan_gemm.comp
T

71 lines
1.9 KiB
Plaintext
Raw Normal View History

2026-06-17 17:44:40 +02:00
#version 450
/*
* Iris Vulkan GEMM (f32)
*
* Computes C[M,N] = alpha * op(A)[M,K] @ op(B)[K,N] + beta * C[M,N]
* where op() optionally transposes, matching the BLAS sgemm contract used
* by the Iris kernels layer. Tiled with 16x16 shared-memory blocks.
*
* A, B, C are row-major with leading dims lda, ldb, ldc.
*/
layout(local_size_x = 16, local_size_y = 16) in;
layout(std430, binding = 0) readonly buffer ABuf { float A[]; };
layout(std430, binding = 1) readonly buffer BBuf { float B[]; };
layout(std430, binding = 2) buffer CBuf { float C[]; };
layout(push_constant) uniform PC {
uint M, N, K;
uint lda, ldb, ldc;
uint ta, tb;
float alpha, beta;
} pc;
shared float As[16][16];
shared float Bs[16][16];
void main() {
uint row = gl_GlobalInvocationID.y;
uint col = gl_GlobalInvocationID.x;
uint tx = gl_LocalInvocationID.x;
uint ty = gl_LocalInvocationID.y;
float acc = 0.0;
uint numTiles = (pc.K + 15u) / 16u;
for (uint t = 0u; t < numTiles; t++) {
uint kA = t * 16u + tx; /* column of A loaded by this lane */
uint kB = t * 16u + ty; /* row of B loaded by this lane */
float av = 0.0;
if (row < pc.M && kA < pc.K) {
av = (pc.ta == 0u) ? A[row * pc.lda + kA]
: A[kA * pc.lda + row];
}
As[ty][tx] = av;
float bv = 0.0;
if (col < pc.N && kB < pc.K) {
bv = (pc.tb == 0u) ? B[kB * pc.ldb + col]
: B[col * pc.ldb + kB];
}
Bs[ty][tx] = bv;
barrier();
for (uint k = 0u; k < 16u; k++) {
acc += As[ty][k] * Bs[k][tx];
}
barrier();
}
if (row < pc.M && col < pc.N) {
uint ci = row * pc.ldc + col;
float prev = (pc.beta != 0.0) ? C[ci] : 0.0;
C[ci] = pc.alpha * acc + pc.beta * prev;
}
}